© 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. 31-TRANSCODER-HP
    7. 18612
    Prev
    Next
    INDEX
    Explanations

    overlooking

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_31.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.31.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    æŃ¢
    -0.29
    è¡į
    -0.27
    nos
    -0.25
    ä¸įå¼Ģ
    -0.24
    gone
    -0.24
     æĽ
    -0.24
     Knot
    -0.24
    æĺ¯è°ģ
    -0.24
    ButtonClick
    -0.24
    Dash
    -0.23
    POSITIVE LOGITS
     spons
    0.32
    对çŃĸ
    0.27
    stras
    0.26
    ANK
    0.26
     Offer
    0.25
    éĶļ
    0.24
    é¦ĸä»ĺ
    0.24
     strncpy
    0.24
    ackers
    0.24
     Offers
    0.24
    Activations Density 1.012%

    No Known Activations