© 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. 46276
    Prev
    Next
    INDEX
    Explanations

    Ramanujan sum or girth

    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
    åħħè£ķ
    -0.07
     Gul
    -0.07
    borough
    -0.07
    ôi
    -0.07
    æĸ°éĹ»ä¸Ńå¿ĥ
    -0.07
    ç½ij绾åĮĸ
    -0.06
    ä¸Ģ大åłĨ
    -0.06
     Narendra
    -0.06
     overrun
    -0.06
    ä¿ĿéļľæĢ§
    -0.06
    POSITIVE LOGITS
    anty
    0.09
    æĮĤéĴ©
    0.08
    à¹Īà¸Ńà¸Ļ
    0.07
    éķ¿çĽ¸
    0.07
    -negative
    0.07
    å¨ģ
    0.07
     discriminatory
    0.07
    Resolved
    0.07
     discrimination
    0.07
     disagree
    0.07
    Activations Density 0.002%

    No Known Activations