© 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. 56173
    Prev
    Next
    INDEX
    Explanations

    update or instead

    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
    æľīç»ıéªĮ
    -0.07
    使åij½æĦŁ
    -0.07
    ä¹łæĥ¯äºİ
    -0.06
    ime
    -0.06
    æľīåħ³æ³ķå¾ĭ
    -0.06
     habit
    -0.06
    天çĶŁçļĦ
    -0.06
    ä»¿ä½Ľæĺ¯
    -0.06
    atin
    -0.06
    æĪĸå°Ĩ
    -0.06
    POSITIVE LOGITS
     instead
    0.14
    instead
    0.12
    èĢĮä¸įæĺ¯
    0.11
     Instead
    0.10
     corrected
    0.10
    è¿Ļæīįæĺ¯
    0.10
    Instead
    0.10
     rather
    0.10
    èĢĮéĿŀ
    0.10
     statt
    0.09
    Activations Density 0.513%

    No Known Activations