© 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. 22969
    Prev
    Next
    INDEX
    Explanations

    ----- Original Message -----

    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
    lick
    -0.07
     Fiorent
    -0.07
    oros
    -0.07
    erten
    -0.07
    åı¦ä¸ĢåįĬ
    -0.07
     Caj
    -0.07
    éĴŁ
    -0.06
    ebi
    -0.06
    عة
    -0.06
    äºĭãģ®
    -0.06
    POSITIVE LOGITS
    ×ķ×¢
    0.07
    é«ĺçŃīä¸ĵç§ijåŃ¦æł¡
    0.07
    аÑģÑĤ
    0.07
    æĪIJé¾Ļ
    0.07
    еÑģÑĤв
    0.07
    ç»Ń
    0.06
    opil
    0.06
    ast
    0.06
    åĹ£
    0.06
    andola
    0.06
    Activations Density 0.002%

    No Known Activations