© 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. 142096
    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
    éĴ§
    -0.26
    æĪ¢
    -0.26
    人æĿĥ
    -0.25
    OOT
    -0.25
    essim
    -0.23
     示
    -0.23
    иÑģк
    -0.23
    ToJson
    -0.23
    æļ®
    -0.23
    SOR
    -0.23
    POSITIVE LOGITS
    uke
    0.27
    mdi
    0.27
    èĥ¸æĢĢ
    0.27
    åľ°æ®µ
    0.26
     meis
    0.26
    mailer
    0.25
    åĽłä¸ºä»ĸ
    0.25
     Sentinel
    0.25
    bery
    0.24
     DEA
    0.24
    Activations Density 27.955%

    No Known Activations

    This feature has no known activations.