© 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. 27-TRANSCODER-HP
    7. 56995
    Prev
    Next
    INDEX
    Explanations

    file paths/IDs

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_27.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.27.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ilib
    -0.30
    wend
    -0.28
     alist
    -0.25
    falls
    -0.25
    äºĨèµ·æĿ¥
    -0.25
     Cassidy
    -0.25
    绪
    -0.25
    ispens
    -0.24
    éĩijèŀįå¸Ĥåľº
    -0.24
    ä¼ģä¸ļæıIJä¾Ľ
    -0.24
    POSITIVE LOGITS
    ioned
    0.28
     conectar
    0.28
    connecting
    0.25
    _connect
    0.25
    å¿«æį·
    0.25
    ninger
    0.25
    addons
    0.25
    å¥ī
    0.25
     connects
    0.25
    常年
    0.24
    Activations Density 0.001%

    No Known Activations