© 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. 96766
    Prev
    Next
    INDEX
    Explanations

    technical/medical text

    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
    Not in Any Lists

    No Comments

    Negative Logits
    åİ
    -0.28
     depreci
    -0.26
    ä¸ĢäºĮ
    -0.25
    sparse
    -0.24
    itta
    -0.24
    adies
    -0.24
     rare
    -0.23
    溷
    -0.23
     PURE
    -0.23
    åĴĮæĬĢæľ¯
    -0.23
    POSITIVE LOGITS
    ç»ĻäºĪ
    0.28
    Impl
    0.28
    /oct
    0.27
    uctions
    0.26
    %%%%
    0.25
     bid
    0.24
    -Aug
    0.24
    ä¿İ
    0.23
    ç»ĻäºĪäºĨ
    0.23
     RID
    0.23
    Activations Density 0.109%

    No Known Activations