© 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. 20-TRANSCODER-HP
    7. 141600
    Prev
    Next
    INDEX
    Explanations

    Mixed/assorted text snippets

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_20.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.20.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    getView
    -0.27
    InSection
    -0.26
     shine
    -0.26
     spy
    -0.25
    acer
    -0.25
     position
    -0.25
     passage
    -0.25
     derivative
    -0.24
     holes
    -0.24
    常åĬ¡
    -0.24
    POSITIVE LOGITS
    ogi
    0.34
    æł¡
    0.29
    æĬ±
    0.29
    uali
    0.27
     Govern
    0.27
    xaf
    0.26
     ép
    0.25
    åŁļ
    0.24
    ursions
    0.24
    nost
    0.24
    Activations Density 2.444%

    No Known Activations