© 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. 39858
    Prev
    Next
    INDEX
    Explanations

    objective analysis

    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
    rasz
    -0.07
    åıijçĤİ
    -0.07
     Worldwide
    -0.07
    ç»ıä¹ħ
    -0.07
    æĶ¾è¿ĩ
    -0.07
     infl
    -0.06
    �t
    -0.06
    èĵ¬
    -0.06
    åı¤çİ©
    -0.06
    åį³åĪ°
    -0.06
    POSITIVE LOGITS
    æĸĩæijĺ
    0.07
    ossip
    0.07
    åĽ½äº§
    0.07
    åIJĪä½ľåĬŀåѦ
    0.07
    ç§ijçłĶæĪIJæŀľ
    0.07
     Meny
    0.07
    åįłåħ¨åĽ½
    0.07
    _abstract
    0.07
    Chinese
    0.07
    SYS
    0.07
    Activations Density 0.327%

    No Known Activations