© 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. 64354
    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
    yat
    -0.29
    åıijçİ°èĩªå·±
    -0.28
     drift
    -0.26
    ãģªãģĦãģ§ãģĻ
    -0.26
    æī«ä¸Ģ
    -0.25
    ä»Ķç»Ĩ
    -0.25
    两åı¥
    -0.24
    igar
    -0.24
    ">#
    -0.24
    åIJijçĿĢ
    -0.24
    POSITIVE LOGITS
    regor
    0.28
     respons
    0.25
    CRYPT
    0.25
    tür
    0.24
    enção
    0.24
    :title
    0.24
     RestClient
    0.24
     khá»ķ
    0.24
    opoly
    0.23
    usi
    0.23
    Activations Density 1.788%

    No Known Activations

    This feature has no known activations.