© 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. 30-TRANSCODER-HP
    7. 95044
    Prev
    Next
    INDEX
    Explanations

    medical and scientific research

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_30.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.30.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    odon
    -0.31
    NAS
    -0.24
    æįĨç»ij
    -0.24
    _globals
    -0.24
    èµ·æĿ¥
    -0.24
     TE
    -0.23
    æĶ¶åĪ°
    -0.23
    ('//
    -0.23
    ente
    -0.23
    寮
    -0.23
    POSITIVE LOGITS
    ç´«
    0.34
    igner
    0.31
     purple
    0.28
    æ¸ħé¦Ļ
    0.28
    acio
    0.27
     Purple
    0.26
     Against
    0.25
    ng
    0.25
    ä¼ļéķ¿
    0.25
     Transfer
    0.25
    Activations Density 0.974%

    No Known Activations