© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 4-TRANSCODER-HP
    7. 123
    Prev
    Next
    INDEX
    Explanations

    code/scientific writing

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_4.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.4.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    çļĦä¸ĢéĿ¢
    -0.26
    è°Ľ
    -0.25
    aspect
    -0.24
    æĹħ游èµĦæºIJ
    -0.24
     scanned
    -0.24
    lya
    -0.24
    abox
    -0.24
    planet
    -0.24
    ANA
    -0.24
    ros
    -0.24
    POSITIVE LOGITS
    使å¾Ĺ
    0.26
    ptic
    0.25
    ivity
    0.25
    enant
    0.25
    ault
    0.24
    ,eg
    0.24
     ARGS
    0.24
    Synopsis
    0.24
    ãģķãģĽ
    0.24
    pliance
    0.24
    Activations Density 0.008%

    No Known Activations