© 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. 8742
    Prev
    Next
    INDEX
    Explanations

    News articles

    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
    gings
    -0.26
    åĬ£
    -0.25
    obot
    -0.25
    -rated
    -0.25
    quire
    -0.25
    åĥ®
    -0.25
     placements
    -0.25
    ä¸ĭéĿ¢
    -0.25
    gest
    -0.24
    qui
    -0.23
    POSITIVE LOGITS
    lover
    0.25
    æģª
    0.25
    èħ®
    0.25
    favicon
    0.24
    饱满
    0.24
    çĮĽ
    0.24
    æĻĤéĸĵãģĮ
    0.24
    StateToProps
    0.23
     distinct
    0.23
     uniquely
    0.23
    Activations Density 0.016%

    No Known Activations