© 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. 26501
    Prev
    Next
    INDEX
    Explanations

    get to the point

    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
    olib
    -0.09
    locales
    -0.08
    igno
    -0.08
    uszcz
    -0.08
     memperm
    -0.08
    áf
    -0.08
    tanda
    -0.08
    åĽ¾çīĩç´łæĿIJ
    -0.08
    ัà¹Īà¸Ļ
    -0.08
    çļĦ深度
    -0.08
    POSITIVE LOGITS
     briefly
    0.09
    é¢ĺæĦı
    0.07
    交代
    0.07
    è®°
    0.06
    æ²ī
    0.06
    ç®Ģè¦ģ
    0.06
     general
    0.06
    æī¿è®¤
    0.06
     adm
    0.06
    ä»ĭç»į
    0.06
    Activations Density 0.002%

    No Known Activations