© 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. 19-TRANSCODER-HP
    7. 8668
    Prev
    Next
    INDEX
    Explanations

    1 or 0

    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
    åݻ买
    -0.26
    .slides
    -0.25
    ç»ıæµİ社ä¼ļ
    -0.25
     @[
    -0.25
     Norton
    -0.25
    ç§įç§į
    -0.24
    ä¸ºæľŁ
    -0.24
    aters
    -0.24
    çīĩ
    -0.24
     Gaul
    -0.24
    POSITIVE LOGITS
    owie
    0.25
     sides
    0.24
    缱
    0.24
     اÙĦتش
    0.24
     initi
    0.24
    burst
    0.24
    (PropertyName
    0.24
    enis
    0.24
    èį¡
    0.23
    åĬ¨æľº
    0.23
    Activations Density 0.030%

    No Known Activations