© 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. 39369
    Prev
    Next
    INDEX
    Explanations

    fractions and mathematical expressions

    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
    rž
    -0.06
     polarity
    -0.06
    igny
    -0.06
    ç®ĩ
    -0.06
    亲èĩª
    -0.06
    ENTIC
    -0.06
    aldi
    -0.06
    ãĤ³ãĥŃ
    -0.06
    æĭIJ
    -0.06
    ÙĪاء
    -0.06
    POSITIVE LOGITS
    ownload
    0.08
    Ratio
    0.07
     prezi
    0.07
    Downloading
    0.07
     **ãĢĮ
    0.07
    产åĵģæľįåĬ¡
    0.07
     ratios
    0.07
     huge
    0.07
     vivi
    0.07
    ãĥĥãĤ·ãĥ³ãĤ°
    0.07
    Activations Density 0.002%

    No Known Activations