© 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. 28453
    Prev
    Next
    INDEX
    Explanations

    actions and beliefs

    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
    ä¸Ģåİ»
    -0.08
    éns
    -0.08
    ãģĭãģŃ
    -0.08
    ekin
    -0.07
    katan
    -0.07
    ÐľÐļ
    -0.07
    ykk
    -0.07
    ä¸ĢæľĽ
    -0.07
    bris
    -0.07
    å®Įæ¯ķåIJİ
    -0.07
    POSITIVE LOGITS
    !:
    0.09
    æł·åŃIJ
    0.08
    !
    0.07
     stuff
    0.07
    !,
    0.07
     damned
    0.07
    åIJįåī¯
    0.07
    樣åŃIJ
    0.07
    åĿıäºĭ
    0.07
    éĴ±
    0.06
    Activations Density 0.719%

    No Known Activations