© 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. 13537
    Prev
    Next
    INDEX
    Explanations

    dates and years

    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
    å¢Ł
    -0.07
    ĥ
    -0.07
     pov
    -0.06
     later
    -0.06
    ä¸ĥæĪIJ
    -0.06
    å¤ļå¾Ĺ
    -0.06
    -addons
    -0.06
    akra
    -0.06
    è£
    -0.06
    人ä¸Ģ
    -0.06
    POSITIVE LOGITS
    SCO
    0.08
    ORIGINAL
    0.07
    chg
    0.07
    uÅŁt
    0.07
    arcz
    0.07
    GMT
    0.07
    anggan
    0.07
    âĨĵâĨĵ
    0.07
    å¤ĸåĽ½è¯Ń
    0.07
    æĽ´æĹ©
    0.07
    Activations Density 0.156%

    No Known Activations