© 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. 107620
    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
    ules
    -0.26
    CreateTime
    -0.25
    iname
    -0.25
    ä¸Ģä¸Ŀ
    -0.25
    ãĢĬ
    -0.25
     those
    -0.24
    åIJİèĢħ
    -0.24
    che
    -0.24
     Bik
    -0.24
    erv
    -0.24
    POSITIVE LOGITS
    ãģ³
    0.24
    idente
    0.24
     Wow
    0.24
    emergency
    0.24
    oriously
    0.24
    _race
    0.24
    .pat
    0.23
    empt
    0.23
    enment
    0.23
    æĹ¥è®¯
    0.23
    Activations Density 14.272%

    No Known Activations

    This feature has no known activations.