© 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. 45907
    Prev
    Next
    INDEX
    Explanations

    analytic formulas

    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
    æ§Ľ
    -0.08
    ä»ħåī©
    -0.07
    æİĴéĻ¤
    -0.07
     somehow
    -0.07
    ont
    -0.07
     conflicting
    -0.07
    olare
    -0.07
    åIJĪè§Ħ
    -0.07
     conting
    -0.07
     dummy
    -0.07
    POSITIVE LOGITS
    åĴĮæݨ广
    0.10
     formulas
    0.09
    åı¯ä»¥çĶ±
    0.08
     useful
    0.08
    çĽ¸çŁ¥
    0.08
    æľĢèijĹåIJįçļĦ
    0.08
    åı¯ä»¥çĶ¨äºİ
    0.08
    åıĬåħ¶åºĶçĶ¨
    0.08
    å®ŀçĶ¨çļĦ
    0.08
    æݨ广
    0.08
    Activations Density 0.039%

    No Known Activations