© 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. 21390
    Prev
    Next
    INDEX
    Explanations

    menu, string, electronic, ALS, Pac, archive, respiratory, water, image, toggle

    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
    åĽłä¸ºåľ¨
    -0.08
     _______,
    -0.07
    åĽłä¸ºè¿Ļ
    -0.07
    engang
    -0.07
    并ä¸Ķåľ¨
    -0.07
    Ñħодим
    -0.07
    以èĩ³
    -0.07
    aldas
    -0.07
    eneg
    -0.07
    请æĭ¨æīĵ
    -0.07
    POSITIVE LOGITS
     thereof
    0.11
    æį®æѤ
    0.11
     accordingly
    0.10
    åľ¨åħ¶ä¸Ń
    0.09
    ä¹ŁåĽłæѤ
    0.09
     therein
    0.09
    åľ¨éĤ£éĩĮ
    0.09
    ä¹Łä¸įä¾ĭå¤ĸ
    0.09
     thereafter
    0.08
    亦çĦ¶
    0.08
    Activations Density 0.030%

    No Known Activations