© 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. 107903
    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
     demand
    -0.32
     resource
    -0.30
     optimal
    -0.28
     dane
    -0.28
     decision
    -0.28
    ç¼´
    -0.27
     risk
    -0.27
    dbe
    -0.27
     approach
    -0.26
     f
    -0.26
    POSITIVE LOGITS
    пÑĢе
    0.30
    IFT
    0.29
    åı¦ä¸ĢåįĬ
    0.29
    è¯ł
    0.26
    åĸ½
    0.26
    entine
    0.25
    å§Ķæīĺ
    0.25
    uner
    0.25
    upos
    0.25
    _intr
    0.25
    Activations Density 45.633%

    No Known Activations

    This feature has no known activations.