© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 20715
    Prev
    Next
    INDEX
    Explanations

    adding or removing file features

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    angk
    -0.08
    æĪĸ被
    -0.07
    eker
    -0.07
    Interceptor
    -0.07
    ŃIJ
    -0.07
    建议æĤ¨
    -0.07
    æĪĸéĢļè¿ĩ
    -0.07
    npos
    -0.07
    æĪĸåĽł
    -0.07
    okit
    -0.07
    POSITIVE LOGITS
     properly
    0.07
    çĭIJ
    0.07
     appropriately
    0.07
     missing
    0.07
    å¼ķåħ¥
    0.07
    帽
    0.07
    æĶ¹çĶ¨
    0.07
     previously
    0.06
     clearer
    0.06
    æĽ´ç¬¦åIJĪ
    0.06
    Activations Density 0.155%

    No Known Activations