© 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. 30430
    Prev
    Next
    INDEX
    Explanations

    as

    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
    项
    -0.28
    ITO
    -0.27
    纸
    -0.27
    ela
    -0.27
    acus
    -0.26
    å¿Ĺ强
    -0.26
     navigator
    -0.26
    æĪĺ士
    -0.26
    ç®Ń
    -0.25
    ä¸ĢæŶ
    -0.25
    POSITIVE LOGITS
    gon
    0.29
    è°´
    0.26
    ĺ认
    0.25
     needless
    0.25
    eam
    0.25
    ernal
    0.25
    ampaign
    0.24
    .datab
    0.24
    .rx
    0.23
     Evalu
    0.23
    Activations Density 0.174%

    No Known Activations