© 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. 19336
    Prev
    Next
    INDEX
    Explanations

    Locations with diacritics

    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
    庸
    -0.28
    èĬŁ
    -0.27
    çľĭä»ĸ
    -0.26
    FML
    -0.26
     Stocks
    -0.26
    ieder
    -0.24
    icana
    -0.24
    naz
    -0.24
    ditor
    -0.24
     buc
    -0.24
    POSITIVE LOGITS
    èĤī
    0.30
    çľ¼
    0.28
    æ¹ĥ
    0.27
    rq
    0.26
    è°´
    0.25
    çľ¼éĩĮ
    0.25
    æ±Ĥ
    0.25
     Inc
    0.24
     inc
    0.24
     eleg
    0.24
    Activations Density 0.010%

    No Known Activations