© 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. 22-TRANSCODER-HP
    7. 130163
    Prev
    Next
    INDEX
    Explanations

    Question words/pronouns

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_22.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.22.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    湫
    -0.30
     testimon
    -0.27
    她æĺ¯
    -0.27
    çıº
    -0.26
     shaft
    -0.25
    éĤ¦
    -0.23
     DIST
    -0.23
     saf
    -0.23
    æ¯ķç«Ł
    -0.23
    aptcha
    -0.23
    POSITIVE LOGITS
    çݯæ¯Ķ
    0.28
    ITIVE
    0.27
    æĪijä¸Ģ缴
    0.26
    Dom
    0.25
    _warnings
    0.24
    :`
    0.24
    odie
    0.24
    ÐĵлавнаÑı
    0.23
    ä¸ĬæĿ¥
    0.23
    .Hosting
    0.23
    Activations Density 0.012%

    No Known Activations