© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 19-TRANSCODER-HP
    7. 7058
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
     fier
    -0.28
    pose
    -0.26
    iap
    -0.26
    pins
    -0.26
    iat
    -0.25
    pared
    -0.25
     vacuum
    -0.25
     Brend
    -0.24
     parcel
    -0.24
    oten
    -0.24
    POSITIVE LOGITS
     INCIDENTAL
    0.26
    uran
    0.26
    é³¢
    0.25
    .RegisterType
    0.25
    æ°ª
    0.25
    ä¹Įåħĭ
    0.25
    ðŁĩ¨
    0.25
    æķ´ä½ĵ
    0.25
     regularly
    0.25
    çļĦçľ¼
    0.25
    Activations Density 1.359%

    No Known Activations

    This feature has no known activations.