© 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. 141285
    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
    frey
    -0.25
    agen
    -0.25
    erk
    -0.25
    nten
    -0.24
    lor
    -0.24
    compose
    -0.24
    ç¿»å¼Ģ
    -0.23
    por
    -0.23
    ovic
    -0.23
     Por
    -0.23
    POSITIVE LOGITS
    è¡ĮåĬ¨
    0.28
    èĩ£
    0.28
    ä¹ł
    0.27
    ç¿Ĵ
    0.25
    ç»ĥä¹ł
    0.25
    ewidth
    0.24
    è¡Įåĭķ
    0.24
     thá»ıa
    0.23
    -use
    0.23
    æŶéĹ´åĨħ
    0.23
    Activations Density 1.150%

    No Known Activations

    This feature has no known activations.