© 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. 141967
    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
    éĻĦåĬł
    -0.28
    群
    -0.26
    æī¹
    -0.26
    çļĦéĤ£ç§į
    -0.26
    èĭ±éĽĦ
    -0.26
    lining
    -0.26
    åħ¬ç¤º
    -0.26
    Hero
    -0.26
    WithName
    -0.25
    æĶ¯æĮģ
    -0.25
    POSITIVE LOGITS
    æ·ĭ
    0.27
    eree
    0.26
     downt
    0.25
    umont
    0.25
    èĢĮåĩº
    0.25
    иваеÑĤ
    0.23
    asthan
    0.23
     PyQt
    0.23
     jog
    0.23
    ä¸į大
    0.23
    Activations Density 19.430%

    No Known Activations

    This feature has no known activations.