© 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. 45017
    Prev
    Next
    INDEX
    Explanations

    first, from, source

    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
    ly
    -0.08
    бак
    -0.07
     Paige
    -0.07
    ä¸ĵæłıæĶ¶å½ķ该åĨħ容
    -0.07
    åİĨåı²ä¿¡æģ¯
    -0.06
    ely
    -0.06
    LY
    -0.06
     íķĺëĤĺë¡ľ
    -0.06
    é¦ģ
    -0.06
    ä¹Łæĺ¯æľĢ
    -0.06
    POSITIVE LOGITS
    è¿Ļè¾¹
    0.10
    è¿Ļè¾¹çļĦ
    0.09
    éĢĻéĤĬ
    0.09
    andon
    0.08
    æĪijåĴĮæĪijçļĦ
    0.07
    USR
    0.07
    linky
    0.07
    otec
    0.07
    åįģä¸ĥæĿ¡
    0.07
    主åĬ¨åIJij
    0.07
    Activations Density 0.066%

    No Known Activations