© 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. 29340
    Prev
    Next
    INDEX
    Explanations

    (

    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
    è¨Ģ
    -0.26
    à¹Ģย
    -0.24
    anguard
    -0.23
    è¯Ŀè¯Ń
    -0.23
    Tom
    -0.23
    ways
    -0.22
     Tom
    -0.22
    ted
    -0.22
    atro
    -0.22
    _JO
    -0.22
    POSITIVE LOGITS
     amp
    0.27
    ihar
    0.26
    زÙĬد
    0.22
    (sem
    0.22
    meno
    0.22
     <<=
    0.22
     yarı
    0.21
    åªĴ
    0.21
     missed
    0.21
    erior
    0.21
    Activations Density 2.451%

    No Known Activations