© 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. 28125
    Prev
    Next
    INDEX
    Explanations

    code or technical abbreviations

    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
    ãģ¨ãģĦãģĪãģ°
    -0.08
    êµ°ìĿĢ
    -0.07
    ãĤīãģ¯
    -0.07
    çıŃéĽĨä½ĵ
    -0.07
    çīĪæĿĥå±ŀäºİ
    -0.07
    ãģ¨è¨ĢãģĪãģ°
    -0.07
    缸åħ³æݨèįIJ
    -0.07
    éĶ¦æ¶Ľ
    -0.07
    tenham
    -0.07
    缮çļĦåľ¨äºİ
    -0.07
    POSITIVE LOGITS
    afari
    0.06
    +xml
    0.06
     perk
    0.06
    令
    0.06
    igated
    0.06
    èijĽ
    0.06
    æīĢ
    0.06
    mu
    0.06
    çĶŁçļĦ
    0.06
    æ¡
    0.06
    Activations Density 0.012%

    No Known Activations