© 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. 29267
    Prev
    Next
    INDEX
    Explanations

    the

    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
    .spotify
    -0.27
    ÑĤÑĢа
    -0.26
    è¿Ļåı¥è¯Ŀ
    -0.26
    ostringstream
    -0.25
     scale
    -0.25
     Frankfurt
    -0.25
    ovi
    -0.25
     mit
    -0.25
    .slim
    -0.25
     Mit
    -0.25
    POSITIVE LOGITS
     mats
    0.29
    ä¸ĢåĽ¢
    0.28
    çĶµå·¥
    0.27
    aits
    0.27
     caucus
    0.26
    æŀķ头
    0.26
    ä¿ĥ
    0.26
    iston
    0.25
     promot
    0.25
    Ng
    0.25
    Activations Density 0.601%

    No Known Activations