© 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. 49794
    Prev
    Next
    INDEX
    Explanations

    integral calculus and derivatives

    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
    éĶ¤
    -0.07
    sockopt
    -0.07
    åį«ä¸ľ
    -0.07
    jos
    -0.06
    ุà¸ĺ
    -0.06
    erals
    -0.06
     telef
    -0.06
     telefon
    -0.06
    èģĺ
    -0.06
    æ·ĺæ±°
    -0.06
    POSITIVE LOGITS
    ivative
    0.08
    adian
    0.08
    帰
    0.08
     tyt
    0.07
     indefinite
    0.07
    é¡·
    0.07
    èݱ德
    0.07
    нÑĤе
    0.07
    åķĨæĬ¥
    0.07
    pace
    0.07
    Activations Density 0.008%

    No Known Activations