© 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. 46544
    Prev
    Next
    INDEX
    Explanations

    mathematical notation and coding symbols

    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
    alti
    -0.07
    éªı
    -0.07
    imon
    -0.07
     âĤ¬.
    -0.07
    коÑĤа
    -0.07
    å¾ĭå·±
    -0.07
    imai
    -0.07
    æľ¬èģĮå·¥ä½ľ
    -0.07
    kinson
    -0.07
    POSITIVE LOGITS
    asten
    0.08
    ouz
    0.08
     unlimited
    0.07
    []>(
    0.07
    æĸ°éĥ½
    0.06
    ÃīT
    0.06
    pragma
    0.06
    æĥħåĨµè¿Ľè¡ĮäºĨ
    0.06
    dej
    0.06
    оÑĢо
    0.06
    Activations Density 0.002%

    No Known Activations