© 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. 33848
    Prev
    Next
    INDEX
    Explanations

    protein formula

    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
    éĽĨä¸Ń
    -0.09
    éĽĨä¸Ń度
    -0.08
    对æķ´ä¸ª
    -0.08
    /single
    -0.08
     concentr
    -0.07
    对äºİä¸Ģ个
    -0.07
    .Batch
    -0.07
     stationary
    -0.07
    åįķæīĵ
    -0.07
    åľ¨å°ı
    -0.07
    POSITIVE LOGITS
    çĶ¨æ¸ħæ°´
    0.10
     Edelst
    0.09
    äºĶè¡Įå±ŀ
    0.09
    ä¸į带
    0.08
    INARY
    0.08
    æł¼éĽ·
    0.08
     mê
    0.08
    代è´Ń
    0.08
    纯åĩĢæ°´
    0.08
     purely
    0.08
    Activations Density 0.401%

    No Known Activations