© 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. 27-TRANSCODER-HP
    7. 57776
    Prev
    Next
    INDEX
    Explanations

    crime and legal matters

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_27.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.27.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    lots
    -0.25
    oth
    -0.25
    PACK
    -0.25
    styleType
    -0.24
    aver
    -0.24
    acerb
    -0.24
    лиÑĤ
    -0.23
    <Result
    -0.23
    .addObject
    -0.23
    ä¸Ģç¯ĩæĸĩç«ł
    -0.23
    POSITIVE LOGITS
    endor
    0.30
    tridge
    0.27
    inde
    0.26
    alted
    0.26
    åŀł
    0.26
    æ§Ľ
    0.26
    .inflate
    0.25
    eyJ
    0.25
    责任å¿ĥ
    0.25
    åħĭæĸ¯
    0.24
    Activations Density 0.005%

    No Known Activations