© 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. 29318
    Prev
    Next
    INDEX
    Explanations

    would

    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
    涯
    -0.32
    大èĥĨ
    -0.28
    箫
    -0.25
    icação
    -0.25
    è£Ķ
    -0.25
    ä¸Ģ款
    -0.25
    好å¥ĩå¿ĥ
    -0.25
    ç©¿
    -0.24
    .proto
    -0.24
    -port
    -0.24
    POSITIVE LOGITS
    æĭĪ
    0.29
    idden
    0.27
    .magnitude
    0.27
    cum
    0.26
     assessed
    0.25
    æŃ£
    0.25
     cum
    0.25
     Cum
    0.24
    zo
    0.23
    dzi
    0.23
    Activations Density 1.901%

    No Known Activations