© 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 EvalsExportsinterp-engineNEWAPI 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. 81653
    Prev
    Next
    INDEX
    Explanations

    fairly

    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
     overcome
    -0.07
    ου
    -0.07
    -0.07
    ($('<
    -0.06
     aprove
    -0.06
     지난
    -0.06
    🎼
    -0.06
    动员
    -0.06
    paRepository
    -0.06
     adverse
    -0.06
    POSITIVE LOGITS
    .special
    0.07
    题
    0.07
    惺
    0.07
    铤
    0.07
     chaos
    0.07
     Temp
    0.07
    问题
    0.06
    Battle
    0.06
    cher
    0.06
    /DD
    0.06
    Activations Density 0.017%

    No Known Activations