© 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. 141105
    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
    lier
    -0.30
    åıĤèĢĥ
    -0.29
     ÑģÑģÑĭл
    -0.28
    nement
    -0.27
    èĴĻ
    -0.26
    çİ°
    -0.26
     *</
    -0.25
    åĿĩ
    -0.25
    zcze
    -0.25
    ë§ģ
    -0.25
    POSITIVE LOGITS
     pathology
    0.28
    åı£æ°´
    0.26
     phon
    0.25
     motivo
    0.25
    upt
    0.25
    ç¿Ĵæħ£
    0.24
     funny
    0.24
     lively
    0.23
    人æ°Ķ
    0.23
     Kas
    0.23
    Activations Density 3.679%

    No Known Activations

    This feature has no known activations.