© 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. 30202
    Prev
    Next
    INDEX
    Explanations

    Chan

    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
    ç¬Ĭ
    -0.28
    .Entry
    -0.27
    æĮ£
    -0.26
     entrance
    -0.26
    åħ¥
    -0.26
    èģ¿
    -0.25
    æ¿®
    -0.25
     Äijấy
    -0.25
    åħ¥å¸Ĥ
    -0.24
    .finished
    -0.24
    POSITIVE LOGITS
    å¤ĩ
    0.27
    erve
    0.27
     Electoral
    0.27
    ért
    0.26
    lek
    0.26
    饱
    0.26
     EXPRESS
    0.25
    ho
    0.25
    ultan
    0.25
     Hor
    0.24
    Activations Density 8.562%

    No Known Activations