© 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. 32-TRANSCODER-HP
    7. 42819
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_32.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.32.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    USR
    -0.31
    itioner
    -0.30
    ed
    -0.27
    èħĭ
    -0.26
    mony
    -0.26
    DTD
    -0.25
     Nurs
    -0.25
    详ç»Ĩ
    -0.25
    ewear
    -0.24
    ono
    -0.24
    POSITIVE LOGITS
     from
    0.30
     upon
    0.29
    ä»İ
    0.26
    uve
    0.26
    èĥŀ
    0.25
     component
    0.24
     stamp
    0.24
    erna
    0.24
    ouns
    0.24
    æ²½
    0.24
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.