© 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. 10556
    Prev
    Next
    INDEX
    Explanations

    same system

    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
    Nic
    -0.07
     }),
    -0.06
    ours
    -0.06
    æµı
    -0.06
    _lite
    -0.06
    çİ°ä½ı
    -0.06
     Nic
    -0.06
     play
    -0.06
    åħĭèݱ
    -0.06
     acc
    -0.06
    POSITIVE LOGITS
    inz
    0.09
    irtual
    0.07
    çļĦéĤ£ç§į
    0.07
    azen
    0.07
    enor
    0.07
     thereof
    0.07
     Gallagher
    0.07
     ÙħÙĨÙĩ
    0.07
    avel
    0.07
    çĶ¨åĪĢ
    0.07
    Activations Density 0.386%

    No Known Activations