© 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. 79577
    Prev
    Next
    INDEX
    Explanations

    code

    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
    驾照
    -0.07
    Ӂ
    -0.07
    (create
    -0.07
     grandparents
    -0.07
    illaume
    -0.07
     Corrections
    -0.06
     jurors
    -0.06
    副作用
    -0.06
     MagicMock
    -0.06
     suspicious
    -0.06
    POSITIVE LOGITS
    %;">
    0.07
    %;"
    0.07
    等领域
    0.07
    >${
    0.07
     qb
    0.07
    Bean
    0.07
     phần
    0.07
    halt
    0.07
    DEC
    0.07
     сли
    0.07
    Activations Density 0.009%

    No Known Activations