© 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. 12-TRANSCODER-HP
    7. 22157
    Prev
    Next
    INDEX
    Explanations

    stomach

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_12.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.12.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    jun
    -0.27
    FP
    -0.26
    ulf
    -0.26
     Parr
    -0.26
    åľ°çľĭçĿĢ
    -0.26
    祧
    -0.25
    çģ¶
    -0.25
    .transition
    -0.25
     fier
    -0.24
    æľĽçĿĢ
    -0.24
    POSITIVE LOGITS
    stick
    0.27
    arding
    0.25
    æĮģå¹³
    0.25
    åĪĽ
    0.25
    etime
    0.25
    arra
    0.24
    çı©
    0.24
     sus
    0.24
    åIJij举
    0.23
    ä¸įå®Į
    0.23
    Activations Density 0.018%

    No Known Activations