© 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. 64440
    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
    enz
    -0.28
    EEK
    -0.27
    <context
    -0.27
    adium
    -0.25
    è¿ŀå¤ľ
    -0.25
    uÃŃ
    -0.25
    æIJĤ
    -0.24
    opies
    -0.24
    LIKELY
    -0.23
    AFX
    -0.23
    POSITIVE LOGITS
    Object
    0.26
    \Id
    0.26
    å½±åĵįåĬĽ
    0.25
    \Web
    0.25
    body
    0.25
    好çļĦ
    0.25
    iva
    0.25
    amen
    0.24
    getField
    0.24
    客æ°Ķ
    0.24
    Activations Density 4.180%

    No Known Activations

    This feature has no known activations.