© 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. 19039
    Prev
    Next
    INDEX
    Explanations

    solder

    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
    éĺµ
    -0.28
     Cut
    -0.27
    .substr
    -0.27
     Odds
    -0.27
     Alphabet
    -0.26
    Substring
    -0.25
    ASI
    -0.25
     atrás
    -0.25
    bis
    -0.25
     Drill
    -0.25
    POSITIVE LOGITS
     pl
    0.28
    æĸĻ
    0.28
     lump
    0.26
     lattice
    0.26
     litter
    0.26
    ä¸Ģåī¯
    0.25
     Mater
    0.25
    POINTS
    0.25
    pl
    0.25
    estone
    0.25
    Activations Density 0.013%

    No Known Activations