© 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. 10445
    Prev
    Next
    INDEX
    Explanations

    course

    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
    概
    -0.07
    imization
    -0.07
     exclusion
    -0.07
    inity
    -0.07
     missile
    -0.07
     Mongolia
    -0.06
    _processing
    -0.06
     svm
    -0.06
    ="",
    -0.06
     Preference
    -0.06
    POSITIVE LOGITS
     Handy
    0.07
    arded
    0.07
     Eight
    0.07
    手机号
    0.07
     Ville
    0.06
    ￭
    0.06
    莸
    0.06
     Platt
    0.06
    ]()↵
    0.06
     YOU
    0.06
    Activations Density 0.021%

    No Known Activations