© 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. 20-TRANSCODER-HP
    7. 141042
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_20.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.20.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    cej
    -0.29
    çļĦè´¨éĩı
    -0.27
    /Edit
    -0.27
    æĪĸå°Ĩ
    -0.26
    éķ¶
    -0.26
    å±¥
    -0.25
    rip
    -0.24
    meal
    -0.24
    ÑĤел
    -0.24
    FIT
    -0.24
    POSITIVE LOGITS
    çĶ¨éĢĶ
    0.30
    é©¾æł¡
    0.25
    electric
    0.24
    idente
    0.24
    ending
    0.24
    缮
    0.23
     ############
    0.23
    isas
    0.23
    umlah
    0.23
     Electricity
    0.23
    Activations Density 8.308%

    No Known Activations

    This feature has no known activations.