© 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. 8794
    Prev
    Next
    INDEX
    Explanations

    Skills and career preparation

    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
    onders
    -0.31
    entially
    -0.27
    pread
    -0.26
    pected
    -0.26
    illion
    -0.26
    pee
    -0.25
    edith
    -0.25
    NewItem
    -0.25
    quez
    -0.25
    icate
    -0.25
    POSITIVE LOGITS
    ä¸įåłª
    0.27
     HAR
    0.26
     altern
    0.25
    rush
    0.25
    è··
    0.25
    itol
    0.25
    Liverpool
    0.25
     demands
    0.24
     downs
    0.24
    @SuppressWarnings
    0.24
    Activations Density 0.013%

    No Known Activations