© 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. 56421
    Prev
    Next
    INDEX
    Explanations

    [@ref

    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
    eka
    -0.07
    imbledon
    -0.06
    ало
    -0.06
     promen
    -0.06
    ÙĪدÙĩ
    -0.06
    èħ¹çĹĽ
    -0.06
    chl
    -0.06
    ม
    -0.06
     Strauss
    -0.06
    ếu
    -0.06
    POSITIVE LOGITS
    ottom
    0.08
    ÌĢ
    0.07
    é¹ıé£ŀ
    0.07
    åij±åij±
    0.07
    å¦Ĥæ½®
    0.07
    å¦Ĥçģ«
    0.07
    aroo
    0.07
     mòn
    0.07
    YC
    0.07
    æĥ³ä½ł
    0.06
    Activations Density 0.134%

    No Known Activations