© 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. 38489
    Prev
    Next
    INDEX
    Explanations

    I would say

    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
    _MISC
    -0.07
     СмоÑĤÑĢиÑĤе
    -0.07
    /misc
    -0.07
    misc
    -0.07
    æģ©æĸ¯
    -0.06
     poj
    -0.06
    ä¸įå¦ĤæĦı
    -0.06
    urit
    -0.06
    éĺ¿å¯Ĩ
    -0.06
    haut
    -0.06
    POSITIVE LOGITS
    âĢ¦but
    0.12
    ä½ĨæĪij们
    0.11
    ä½ĨæĪij
    0.10
    ä½Ĩè¿Ļ
    0.10
    ãģ¾ãģĽãĤĵãģĮ
    0.10
    —but
    0.09
    ä½Ĩè¿Ļç§į
    0.09
    ,but
    0.09
    ä½ĨéĤ£
    0.09
    ä½ĨçĶ±äºİ
    0.08
    Activations Density 0.323%

    No Known Activations