© 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. 141421
    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
    ITO
    -0.29
    BuilderFactory
    -0.29
    ivy
    -0.28
     tot
    -0.27
    awah
    -0.25
    Blue
    -0.24
    è°Ħ
    -0.24
    à¸Ńà¸Ńà¸ģ
    -0.24
     Leafs
    -0.24
    èĵĿ
    -0.23
    POSITIVE LOGITS
    bens
    0.29
    è¿ĺ好
    0.27
    /sites
    0.27
    nte
    0.26
     sog
    0.26
     purchases
    0.26
     sopr
    0.25
     trump
    0.25
    -settings
    0.25
    strup
    0.25
    Activations Density 6.833%

    No Known Activations

    This feature has no known activations.