© 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. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 27157
    Prev
    Next
    INDEX
    Explanations

    advice or suggestions

    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
    Ñĥго
    -0.06
    å¾·æĸ¯
    -0.06
    lsen
    -0.06
    绿èī²éĢļéģĵ
    -0.06
    æģIJ
    -0.06
    æ»ij稽
    -0.06
    atia
    -0.06
    utz
    -0.06
    é´
    -0.05
    feld
    -0.05
    POSITIVE LOGITS
    åľ¨ä»¥åIJİ
    0.08
    acor
    0.08
    äºĨä¸ĭåİ»
    0.07
    飬
    0.07
    建议
    0.07
     UIManager
    0.07
    бал
    0.07
     λοι
    0.07
    æķĻäºİ
    0.07
    ä¸ĭ次
    0.07
    Activations Density 0.088%

    No Known Activations