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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 19-TRANSCODER-HP
    7. 6292
    Prev
    Next
    INDEX
    Explanations

    medical diagnoses

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_19.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.19.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    æľīæĿ¡ä»¶
    -0.27
    putation
    -0.27
    cession
    -0.25
    mercial
    -0.25
     sublicense
    -0.25
    .writerow
    -0.24
    CISION
    -0.24
    éĴĭ
    -0.23
    tron
    -0.23
     Homo
    -0.23
    POSITIVE LOGITS
    ertil
    0.27
     forte
    0.27
    agu
    0.27
    éķ«
    0.26
    addy
    0.26
    tones
    0.25
     kad
    0.24
    ombres
    0.24
     Vers
    0.24
    æªĶ
    0.24
    Activations Density 0.013%

    No Known Activations