© 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. 57279
    Prev
    Next
    INDEX
    Explanations

    new

    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
    ä¸Ģçķª
    -0.31
    åĢ¼å¾Ĺåħ³æ³¨
    -0.29
     mojo
    -0.28
    Mo
    -0.28
    å¼Ģ端
    -0.27
     roads
    -0.26
    æ²Ł
    -0.26
    åıij表äºĨ
    -0.26
     thinkers
    -0.26
    mo
    -0.26
    POSITIVE LOGITS
    orary
    0.27
    åĬ¡
    0.27
     prer
    0.26
    indrical
    0.26
    æĸ¹å½¢
    0.25
     flat
    0.25
     subsidi
    0.24
    é¦Ĵ头
    0.24
    pson
    0.24
     Saturday
    0.24
    Activations Density 0.013%

    No Known Activations