© 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. 107327
    Prev
    Next
    INDEX
    Explanations

    what

    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
    iest
    -0.30
     fray
    -0.27
    çļĦè¯Ŀ
    -0.26
    FromClass
    -0.26
    çļĦ話
    -0.25
    è¯Ŀ
    -0.25
    aban
    -0.24
    âĸ¯
    -0.24
    lion
    -0.24
    ีà¹Ī
    -0.24
    POSITIVE LOGITS
    ä¹Łä¸įåı¯èĥ½
    0.27
    åĨ²çªģ
    0.25
    ä¹Łä¸įä¼ļ
    0.25
    æĽ´å¤§çļĦ
    0.25
     saturated
    0.25
    нал
    0.24
    loads
    0.24
    çļ®
    0.24
    太快
    0.24
    ushman
    0.24
    Activations Density 8.247%

    No Known Activations