© 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. 19400
    Prev
    Next
    INDEX
    Explanations

    search

    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
    sov
    -0.27
    è´§å¸ģ
    -0.26
    moil
    -0.26
    èĩ»
    -0.25
    è´²
    -0.24
    æĹĹ
    -0.23
    æĸĩåĪĽ
    -0.23
    马åħĭ
    -0.23
    ¨¡
    -0.23
    emade
    -0.23
    POSITIVE LOGITS
     terms
    0.54
     term
    0.47
     TERMS
    0.47
     Terms
    0.47
    terms
    0.46
    Terms
    0.46
    term
    0.43
    _terms
    0.43
     TERM
    0.40
    Term
    0.39
    Activations Density 0.270%

    No Known Activations