© 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. 30274
    Prev
    Next
    INDEX
    Explanations

    ART

    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
     subsidi
    -0.30
    çĶ³
    -0.26
    eners
    -0.26
    æī¶
    -0.26
    empre
    -0.25
     Bears
    -0.25
    æľįåĬ¡åĮº
    -0.25
    erves
    -0.24
    èµİ
    -0.24
    สะ
    -0.24
    POSITIVE LOGITS
    mission
    0.29
    pha
    0.29
    åħ¥æĪ·
    0.27
    åĥı个
    0.26
    éĢģ
    0.25
     Frm
    0.25
    ä¸įåĪĨ
    0.25
    æĬ±åĽ¢
    0.25
    éĤĪ
    0.25
     blink
    0.25
    Activations Density 0.635%

    No Known Activations