© 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. 7-RESID-POST-AA
    11. 80988
    Prev
    Next
    INDEX
    Explanations

    written or spoken text

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-qwen2.5-7b-instruct/resid_post_layer_7/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.7.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
     lp
    -0.07
     spindle
    -0.07
    リン
    -0.07
    年人
    -0.06
    倪
    -0.06
    を取り
    -0.06
    icons
    -0.06
     welcoming
    -0.06
    isex
    -0.06
    POSITIVE LOGITS
    关乎
    0.08
    将于
    0.07
     unveiled
    0.07
    猶
    0.06
    .Dec
    0.06
     fan
    0.06
    earn
    0.06
     acceler
    0.06
    ces
    0.06
    也应该
    0.06
    Activations Density 0.252%

    No Known Activations