© 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. 12-TRANSCODER-HP
    7. 22912
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_12.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.12.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    åŃĺ
    -0.27
     blot
    -0.27
    æ¯Ķçİĩ
    -0.26
    æĭŃ
    -0.26
    udent
    -0.26
     commuting
    -0.25
    åİĭ缩
    -0.25
     undercover
    -0.25
    quil
    -0.25
    è¿ĺåı¯ä»¥
    -0.24
    POSITIVE LOGITS
    ä½Ĺ
    0.26
    inition
    0.25
    inka
    0.25
    <String
    0.25
     Tango
    0.25
    æĤ«
    0.24
    halt
    0.24
    çļĦ姿æĢģ
    0.24
    ç¨³åĽº
    0.24
    åĨĻä¸ĭ
    0.23
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.