© 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. 30422
    Prev
    Next
    INDEX
    Explanations

    internet

    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
    æĶ¶
    -0.28
    èĢĻ
    -0.26
     expectancy
    -0.26
    æİ
    -0.25
    enco
    -0.25
    é²ľæĺİ
    -0.25
    模å¼ı
    -0.25
     auprès
    -0.25
    è¡°
    -0.24
    æ¸ħæĸ°
    -0.24
    POSITIVE LOGITS
    åıij
    0.26
    poly
    0.26
    :x
    0.26
    ä¸ĵéĹ¨ä¸º
    0.26
    sumer
    0.25
    .poly
    0.25
    à¸Ĺา
    0.24
    volt
    0.24
     poly
    0.23
     POW
    0.23
    Activations Density 2.690%

    No Known Activations