© 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. 8805
    Prev
    Next
    INDEX
    Explanations

    Numbers

    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
    çľĭçĶµå½±
    -0.29
    yleft
    -0.25
    è´¯
    -0.25
    ượng
    -0.25
    .www
    -0.25
     genre
    -0.23
    çıŃåŃIJæĪIJåijĺ
    -0.23
     getObject
    -0.23
    (configuration
    -0.23
    chwitz
    -0.23
    POSITIVE LOGITS
     Develop
    0.26
    IDS
    0.25
    è¿Ń
    0.24
    仿
    0.23
     Disorder
    0.23
     Fest
    0.23
    eps
    0.23
     walker
    0.23
    pite
    0.23
     Pitt
    0.23
    Activations Density 0.013%

    No Known Activations