© 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. 7922
    Prev
    Next
    INDEX
    Explanations

    advice

    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
    rote
    -0.26
     ******************************************************************************↵
    -0.25
    erness
    -0.24
    Úº
    -0.24
    entifier
    -0.23
     summers
    -0.23
    ..\
    -0.23
    ãģ®ãģĵãģ¨
    -0.23
     AppBundle
    -0.23
     temporary
    -0.22
    POSITIVE LOGITS
    AGE
    0.24
    ån
    0.24
     bomb
    0.24
    alom
    0.23
    stoff
    0.23
     provinc
    0.23
    ÐIJÐĿ
    0.23
    _arr
    0.23
    -ad
    0.23
    даеÑĤÑģÑı
    0.23
    Activations Density 1.016%

    No Known Activations