© 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. 7768
    Prev
    Next
    INDEX
    Explanations

    in

    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
    SETS
    -0.27
    enie
    -0.26
    бед
    -0.25
     fully
    -0.24
     polygon
    -0.23
    ä¸Ģ个人
    -0.23
    /fixtures
    -0.23
    olygon
    -0.23
    è°ª
    -0.23
    -export
    -0.22
    POSITIVE LOGITS
     lá»Ŀi
    0.33
    omatic
    0.32
    .Mode
    0.26
    liquid
    0.26
    werk
    0.25
    pray
    0.24
     briefed
    0.24
    ity
    0.24
    bih
    0.24
    æİ°
    0.24
    Activations Density 0.158%

    No Known Activations