© 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. 30492
    Prev
    Next
    INDEX
    Explanations

    Web content snippets

    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
    OMP
    -0.29
     headline
    -0.26
    ega
    -0.25
    丰å¯Į
    -0.24
    EGA
    -0.24
    plevel
    -0.24
    缺å¸Ń
    -0.24
    .unsubscribe
    -0.24
    æĸ°èģŀ
    -0.24
    鼶åĶ®
    -0.23
    POSITIVE LOGITS
    sil
    0.29
    sess
    0.28
    æ±Ĺ
    0.27
    mia
    0.27
     budd
    0.27
    los
    0.27
    é¹Ħ
    0.26
    ogene
    0.26
    hta
    0.26
    otted
    0.25
    Activations Density 41.076%

    No Known Activations