© 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. 27323
    Prev
    Next
    INDEX
    Explanations

    language codes or abbreviations

    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
    çĬ¶
    -0.09
    ly
    -0.07
    ãģĿ
    -0.07
    деле
    -0.07
    (er
    -0.07
    Ĥ
    -0.07
    çİ·
    -0.07
    åĪ«æıIJ
    -0.06
    æŁĵ
    -0.06
    Ãłng
    -0.06
    POSITIVE LOGITS
    å¢ĥåĨħçļĦ
    0.08
    åĮĪ
    0.08
    мок
    0.08
    ä¸Ģåľ°
    0.08
    åĴĮä¸ŃåĽ½
    0.08
    çŃīåĽ½
    0.07
    ä¸ĢåĽ½
    0.07
    çŃīåľ°çļĦ
    0.07
    ingar
    0.07
    æľĶ
    0.07
    Activations Density 0.166%

    No Known Activations