© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 42393
    Prev
    Next
    INDEX
    Explanations

    comparison operators and assignments

    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
    azan
    -0.06
    è¯¥ç³»ç»Ł
    -0.06
    aram
    -0.06
    è¾Ī
    -0.06
    æ¯Ľæ³½ä¸ľ
    -0.05
    æľ¬åĬŀæ³ķ
    -0.05
    该产åĵģ
    -0.05
    tera
    -0.05
    OnChange
    -0.05
    ensee
    -0.05
    POSITIVE LOGITS
    uze
    0.08
    ä¸İåIJ¦
    0.08
    /not
    0.07
    åĴĮä¿¡æģ¯åĮĸ
    0.07
    ,idx
    0.07
    æĹ©æĹ¥
    0.07
    æĪĸ使çĶ¨
    0.07
     Hause
    0.07
    vez
    0.07
    gfx
    0.07
    Activations Density 0.008%

    No Known Activations