© 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. 58112
    Prev
    Next
    INDEX
    Explanations

    mathematical notation and variables

    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
    agam
    -0.07
    éĴ®
    -0.07
    osa
    -0.07
    åĴĮæŶéĹ´
    -0.06
    way
    -0.06
    WAY
    -0.06
    ÙĤÙħ
    -0.06
    ÃľR
    -0.06
    adang
    -0.05
    allis
    -0.05
    POSITIVE LOGITS
    ippi
    0.09
    kund
    0.08
    perc
    0.08
     Äijạo
    0.08
    cina
    0.07
    ()?.
    0.07
    åı²è¯Ĺ
    0.07
    isoft
    0.07
    Declared
    0.07
    æ´Ľå¤«
    0.07
    Activations Density 0.003%

    No Known Activations