© 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. 29162
    Prev
    Next
    INDEX
    Explanations

    but

    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
    讹
    -0.26
     Seeking
    -0.25
    mare
    -0.25
    åķĸ
    -0.24
    mist
    -0.24
     pitches
    -0.24
    Prem
    -0.24
    isto
    -0.24
     tamp
    -0.24
    磫
    -0.24
    POSITIVE LOGITS
    asley
    0.29
    alers
    0.26
    ([...
    0.26
    éģ¥
    0.24
    æ¸ħéĨĴ
    0.24
    oders
    0.24
    enuity
    0.24
     Tut
    0.24
     hereby
    0.24
     []).
    0.24
    Activations Density 2.541%

    No Known Activations