© 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. 12-TRANSCODER-HP
    7. 23522
    Prev
    Next
    INDEX
    Explanations

    Question words

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_12.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.12.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     div
    -0.26
     dick
    -0.25
    讳
    -0.25
    ÑģÑĤавка
    -0.25
    _IL
    -0.25
    .Il
    -0.23
    æ²»çIJĨ
    -0.23
    èĪ«
    -0.23
     Publié
    -0.23
    ä¸įæŃ»
    -0.23
    POSITIVE LOGITS
    çļĦåŁºç¡Ģ
    0.28
     beneficiaries
    0.26
    osomes
    0.26
    åĽºå®ļ
    0.24
    izo
    0.24
     fixed
    0.24
    acier
    0.23
    ç²ij
    0.23
     vitamins
    0.23
    æĴ¬
    0.23
    Activations Density 0.002%

    No Known Activations