© 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. 75170
    Prev
    Next
    INDEX
    Explanations

    numpy

    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
     testing
    -0.08
    孟
    -0.07
    阁
    -0.07
     Del
    -0.07
     pa
    -0.07
     Cow
    -0.07
     cc
    -0.07
    testing
    -0.07
     Plumbing
    -0.06
    检
    -0.06
    POSITIVE LOGITS
    .Lines
    0.08
     numpy
    0.08
    ===
    0.07
    מדינ
    0.07
     (;;)
    0.07
    不在乎
    0.07
     NSURL
    0.07
    𫑡
    0.07
    を与え
    0.07
    กระจาย
    0.07
    Activations Density 0.003%

    No Known Activations