© 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. 107906
    Prev
    Next
    INDEX
    Explanations

    consistently

    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
     undert
    -0.29
    rew
    -0.28
    管çIJĨ模å¼ı
    -0.27
    RowIndex
    -0.27
    ren
    -0.25
     Order
    -0.25
    hea
    -0.25
    ext
    -0.24
    秩åºı
    -0.24
    第ä¸ĢæĿ¡
    -0.24
    POSITIVE LOGITS
    assin
    0.28
    穷人
    0.27
    achte
    0.27
    essor
    0.27
    epam
    0.26
    į°
    0.25
    NIL
    0.25
    ಪ
    0.24
    amax
    0.24
    ãģ¿ãģª
    0.24
    Activations Density 25.315%

    No Known Activations