© 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. 107862
    Prev
    Next
    INDEX
    Explanations

    programming

    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
    æŁ¥
    -0.26
    æīĵãģ¡
    -0.25
    æ·¤
    -0.25
     nháºŃp
    -0.25
     plainly
    -0.25
    orn
    -0.24
    resses
    -0.24
    è¿Ľåı£
    -0.24
    æĶ¶æĶ¯
    -0.24
    ä¸įéĢļ
    -0.24
    POSITIVE LOGITS
    èħĭ
    0.27
    SID
    0.27
    orate
    0.26
    çļĦ带é¢Ĩ
    0.24
    ,eg
    0.24
    DON
    0.24
    /vnd
    0.24
    举
    0.23
    GUID
    0.23
     evangel
    0.23
    Activations Density 0.932%

    No Known Activations