© 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. Qwen3-4B
    5. 31-TRANSCODER-HP
    7. 19077
    Prev
    Next
    INDEX
    Explanations

    University

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_31.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.31.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    isci
    -0.26
    -wh
    -0.26
    符
    -0.25
    loth
    -0.25
     Pee
    -0.24
    åıijæĸĩ
    -0.24
    .ind
    -0.24
    íݸ
    -0.24
    SG
    -0.24
    iction
    -0.24
    POSITIVE LOGITS
    åIJŀ
    0.25
    uncate
    0.25
    è¿IJè¡Į
    0.25
     punched
    0.25
    æĮł
    0.24
    DRV
    0.24
    åķĨåĵģ
    0.24
     United
    0.24
    osl
    0.24
    é¢Ŀ
    0.24
    Activations Density 0.020%

    No Known Activations