© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 9-TRANSCODER-HP
    7. 29347
    Prev
    Next
    INDEX
    Explanations

    atri

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_9.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.9.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
     strut
    -0.33
    stra
    -0.30
    (Str
    -0.29
     scanner
    -0.27
    clud
    -0.27
    str
    -0.27
    -str
    -0.26
     estr
    -0.26
    ycler
    -0.26
    [str
    -0.26
    POSITIVE LOGITS
    olib
    0.30
    è¿Ļåı¥è¯Ŀ
    0.29
    =./
    0.26
    GMEM
    0.25
    /*----------------------------------------------------------------------------
    0.24
    abouts
    0.24
    ent
    0.24
    ẩn
    0.24
    lya
    0.24
     ActionTypes
    0.24
    Activations Density 1.063%

    No Known Activations