© 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. 24-TRANSCODER-HP
    7. 149984
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_24.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.24.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    _CID
    -0.25
    å¤§èµĽ
    -0.25
    ,private
    -0.25
    óa
    -0.23
     competitions
    -0.23
    è¿ľç¨ĭ
    -0.23
     offline
    -0.23
    uish
    -0.23
    /exec
    -0.23
    vida
    -0.23
    POSITIVE LOGITS
    转
    0.27
    ä¸İä¸ŃåĽ½
    0.26
     –
    0.25
    å®ŀçī©
    0.25
    讲è¯Ŀ
    0.24
    ä¸įåIJĮç¨ĭ度
    0.24
     Ful
    0.24
    款
    0.23
    åĵį
    0.23
    饶
    0.23
    Activations Density 0.113%

    No Known Activations

    This feature has no known activations.