© 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. 30-TRANSCODER-HP
    7. 96580
    Prev
    Next
    INDEX
    Explanations

    research studies

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_30.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.30.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Remain
    -0.28
     allowances
    -0.28
     remainder
    -0.27
    ä¸įå®Į
    -0.26
    fbe
    -0.26
     stay
    -0.25
     allowance
    -0.25
    _pb
    -0.25
     reduction
    -0.24
    anteed
    -0.24
    POSITIVE LOGITS
    æıIJä¾ĽäºĨ
    0.42
     provides
    0.39
     identifies
    0.38
    æıIJä¾Ľ
    0.37
     identification
    0.34
     ident
    0.34
     introduces
    0.33
    .ident
    0.33
     fills
    0.33
     filled
    0.32
    Activations Density 0.892%

    No Known Activations