© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 30541
    Prev
    Next
    INDEX
    Explanations

    mathematical properties

    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
    outers
    -0.07
    itta
    -0.07
    AsString
    -0.07
    åıĬè¦ģæ±Ĥ
    -0.07
    okes
    -0.07
    ']>
    -0.07
    sett
    -0.07
    iba
    -0.07
    æł¼æł¼
    -0.07
    åŃ©åŃIJçļĦæĪIJéķ¿
    -0.07
    POSITIVE LOGITS
    dor
    0.07
    ä¸İéĿŀ
    0.07
    并ä¸Ķè¿ĺ
    0.07
    esis
    0.07
    виÑĤ
    0.06
    à¸Ļาม
    0.06
    æĹłçĸij
    0.06
    ofday
    0.06
    herit
    0.06
    lify
    0.06
    Activations Density 0.007%

    No Known Activations