© 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. 35-TRANSCODER-HP
    7. 39373
    Prev
    Next
    INDEX
    Explanations

    The beginning of documents

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_35.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.35.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     give
    -0.26
     mies
    -0.25
    帮å¿Ļ
    -0.25
     recap
    -0.25
    æĬ¥éħ¬
    -0.24
     gives
    -0.24
    缪
    -0.24
     Rooms
    -0.24
    没人
    -0.24
     depreci
    -0.23
    POSITIVE LOGITS
    ime
    0.28
    kontakte
    0.26
    incipal
    0.26
    im
    0.25
    ders
    0.25
    ãģĦãģ£ãģŁ
    0.23
    piece
    0.23
    orda
    0.23
     other
    0.23
    opensource
    0.23
    Activations Density 0.007%

    No Known Activations