© 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. 18-TRANSCODER-HP
    7. 88528
    Prev
    Next
    INDEX
    Explanations

    Code, math, and technical language

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_18.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.18.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Skywalker
    -0.27
    @Api
    -0.26
    å¥ĸ
    -0.26
    å·´åŁº
    -0.26
    éĴ¡
    -0.24
    æ¦
    -0.24
    举
    -0.24
    æĻļ
    -0.24
    以éĺ²
    -0.24
    è³ŀ
    -0.24
    POSITIVE LOGITS
     Percent
    0.32
     Honest
    0.28
     Notices
    0.27
     Percentage
    0.27
    ematics
    0.26
    fic
    0.26
     percentages
    0.26
     mathematics
    0.25
     percent
    0.25
    ards
    0.25
    Activations Density 13.653%

    No Known Activations