© 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. 29105
    Prev
    Next
    INDEX
    Explanations

    Code/programming

    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
    æĭĨè¿ģ
    -0.31
    _algo
    -0.28
    åIJĪ
    -0.28
    ä¸ĭä¸Ģ
    -0.27
    roat
    -0.25
    åħ³åĪĩ
    -0.25
     fences
    -0.25
     iv
    -0.25
    ived
    -0.24
     displacement
    -0.24
    POSITIVE LOGITS
    spl
    0.28
     totalTime
    0.26
    addtogroup
    0.25
    Rated
    0.25
    Neill
    0.24
    otto
    0.24
    èĩªåĬ©
    0.24
    深交
    0.24
    .ext
    0.24
     endwhile
    0.23
    Activations Density 5.981%

    No Known Activations