© 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. 23702
    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
    ноÑģÑĤей
    -0.30
    ä¸ŃåİŁ
    -0.28
    otch
    -0.28
    ä¸Ńåħ³
    -0.26
    (feature
    -0.26
    èªī
    -0.26
    portion
    -0.26
     feature
    -0.25
    è¯Ń
    -0.25
    stro
    -0.25
    POSITIVE LOGITS
    çģµæĦŁ
    0.28
    cou
    0.25
    hoff
    0.25
     recursively
    0.25
     translated
    0.24
    Writing
    0.24
     mobs
    0.23
    minster
    0.23
    ç»ı纪
    0.23
    kah
    0.23
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.