© 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. 24866
    Prev
    Next
    INDEX
    Explanations

    RUN: commands

    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
    olino
    -0.08
    ä»İæѤ
    -0.08
    å°Ķåħĭ
    -0.08
     Annunci
    -0.07
    Ùĥرة
    -0.07
    оÑĩно
    -0.07
    UMO
    -0.07
    æĪijçļĦç¥Ŀç¦ı
    -0.07
    TS
    -0.07
    åľ¨æŁIJ
    -0.07
    POSITIVE LOGITS
    lass
    0.07
    ovati
    0.06
     regarding
    0.06
    é¶
    0.06
     flawless
    0.06
    Disallow
    0.06
    æľ¬å½ĵãģ«
    0.06
    é¢ĺ为
    0.06
     thoroughly
    0.06
    mara
    0.06
    Activations Density 0.002%

    No Known Activations