© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 20-TRANSCODER-HP
    7. 142339
    Prev
    Next
    INDEX
    Explanations

    health information and awareness

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_20.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.20.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    orque
    -0.26
    å½¼ãĤī
    -0.25
    ç©¿
    -0.25
    ä»ĸä»¬åľ¨
    -0.25
     loop
    -0.25
    æĪ³
    -0.24
     siz
    -0.24
    oppable
    -0.24
     scheduling
    -0.24
    ằ
    -0.24
    POSITIVE LOGITS
    thed
    0.27
    SSL
    0.24
    works
    0.24
    *)(
    0.24
    åĩĢ
    0.24
     whore
    0.23
    åĩłå¼ł
    0.23
     Wild
    0.23
    olio
    0.23
    ÑĤÑģÑı
    0.23
    Activations Density 10.698%

    No Known Activations