© 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. 7759
    Prev
    Next
    INDEX
    Explanations

    muzzle

    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
    .remote
    -0.07
     Orch
    -0.07
     hypoth
    -0.07
    ighborhood
    -0.06
    oo
    -0.06
    =date
    -0.06
    physics
    -0.06
     newest
    -0.06
    *X
    -0.06
     lashes
    -0.06
    POSITIVE LOGITS
    مسألة
    0.07
    ;',↵
    0.07
     Clifford
    0.07
     Legacy
    0.07
    King
    0.07
    รว
    0.07
    とい
    0.07
    修改
    0.07
    кра
    0.07
     „
    0.07
    Activations Density 0.511%

    No Known Activations