© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Qwen2.5-7B-IT
    7. Resid Post - 131k
    9. 15-RESID-POST-AA
    11. 84061
    Prev
    Next
    INDEX
    Explanations

    negativity and criticism

    np_max-act · gemini-2.0-flash

    Finds mentions of political organizations, lobbying groups, or institutional power (names or references to such entities).

    oai_token-act-pair · gpt-5-miniTriggered by @vetterc0
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-qwen2.5-7b-instruct/resid_post_layer_15/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    .↵↵↵↵↵↵
    -0.07
    Throws
    -0.07
     <-
    -0.07
     aValue
    -0.07
    addComponent
    -0.07
     cig
    -0.07
     beautiful
    -0.07
    Drive
    -0.06
     punishable
    -0.06
    stairs
    -0.06
    POSITIVE LOGITS
    逆转
    0.08
     보내
    0.07
     Mechan
    0.07
    物资
    0.07
    之时
    0.07
    了他的
    0.07
     BASE
    0.07
    大的
    0.06
     abolish
    0.06
     решения
    0.06
    Activations Density 0.214%

    No Known Activations