© 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. 25235
    Prev
    Next
    INDEX
    Explanations

    potential and state

    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
    éĽªå±±
    -0.07
    ciel
    -0.07
    å®Ľ
    -0.07
    æľ¬æĿ¥å°±
    -0.07
     conflic
    -0.07
    å¤ļç±³
    -0.07
     jaz
    -0.07
    ãģĹãĤĩãģĨ
    -0.07
    é£İæļ´
    -0.07
    igos
    -0.07
    POSITIVE LOGITS
    æıĴ
    0.07
     Schild
    0.07
    åıªè¦ģæĺ¯
    0.07
    好å¥ĩ
    0.07
    custom
    0.07
    æĸ¯èĴĤ
    0.07
     satisfying
    0.07
     conform
    0.06
    导åĩº
    0.06
    rom
    0.06
    Activations Density 0.034%

    No Known Activations