© 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. 8438
    Prev
    Next
    INDEX
    Explanations

    requires javascript or subscription

    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
    حرص
    -0.07
     MUCH
    -0.07
     impulse
    -0.07
     TOTAL
    -0.06
     Attendance
    -0.06
    החלטת
    -0.06
    Response
    -0.06
    ᯙ
    -0.06
     Antony
    -0.06
    -License
    -0.06
    POSITIVE LOGITS
    NTSTATUS
    0.08
    妇
    0.07
    toHaveBeenCalledWith
    0.07
     대부
    0.07
    辫
    0.07
    他认为
    0.07
    0.07
    僰
    0.07
     spent
    0.07
    剩
    0.07
    Activations Density 0.149%
    No Known Activations