© 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. 11294
    Prev
    Next
    INDEX
    Explanations

    programming loop index

    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
    ç«ĻåĨħæIJľç´¢
    -0.07
    appendTo
    -0.07
    illus
    -0.07
    blr
    -0.07
    Geb
    -0.07
    çݰ代人
    -0.07
    inado
    -0.07
    çĥŁéħĴ
    -0.06
    çĥŁèįī
    -0.06
     tobacco
    -0.06
    POSITIVE LOGITS
    æĺĬ
    0.07
    olik
    0.07
    atha
    0.07
    ĸ
    0.07
    ä¸½å¨ľ
    0.07
    èĤ¥
    0.06
    opher
    0.06
    丽èİİ
    0.06
     Vend
    0.06
    æĮĩçĿĢ
    0.06
    Activations Density 0.036%

    No Known Activations