© 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. 96035
    Prev
    Next
    INDEX
    Explanations

    scientific technical texts

    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
    oon
    -0.28
    Ra
    -0.28
    ensem
    -0.27
    lij
    -0.25
    setId
    -0.25
    qli
    -0.24
    ict
    -0.24
    ëŁ¼
    -0.24
    :def
    -0.23
    é¢Ŀ
    -0.23
    POSITIVE LOGITS
    è·³
    0.24
     NOTICE
    0.24
     piss
    0.24
    charges
    0.24
    åīįä¸ī
    0.23
    .normalized
    0.23
    unft
    0.23
     Booker
    0.23
    pee
    0.23
    轶
    0.23
    Activations Density 0.883%

    No Known Activations