© 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. 8878
    Prev
    Next
    INDEX
    Explanations

    source code

    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
    å¾®éĩı
    -0.27
    ì¼Ģ
    -0.26
    äºĴ
    -0.26
    å®ŀä¹ł
    -0.26
    thesis
    -0.26
    ,Th
    -0.25
    yz
    -0.25
    ãģ¾
    -0.25
    åĢį
    -0.25
    åįķ项
    -0.25
    POSITIVE LOGITS
    iya
    0.31
    ktop
    0.28
    .asp
    0.27
    eya
    0.26
     Britt
    0.25
    dorf
    0.24
    åĽ½æľīä¼ģä¸ļ
    0.24
    天èĬ±æĿ¿
    0.24
    æľºåħ³
    0.24
    uated
    0.24
    Activations Density 0.001%

    No Known Activations