© 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. 22-TRANSCODER-HP
    7. 111853
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_22.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.22.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    è¾ĺ
    -0.29
    plements
    -0.27
    aad
    -0.26
    ä»£è¡¨åĽ¢
    -0.25
    bü
    -0.25
    ç¼Ĵ
    -0.25
     nond
    -0.25
    âĬ£
    -0.24
    橱
    -0.24
     immun
    -0.24
    POSITIVE LOGITS
    иÑĢа
    0.29
    åľ¨åIJĮä¸Ģ
    0.28
     reflect
    0.28
    reflect
    0.27
    .Profile
    0.26
    UN
    0.25
    째
    0.25
    argest
    0.25
    第ä¸ĢæŃ¥
    0.24
    以ä¸ĬçļĦ
    0.24
    Activations Density 0.003%

    No Known Activations

    This feature has no known activations.