© 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. 56727
    Prev
    Next
    INDEX
    Explanations

    conversion methods from certain surfaces

    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
     complementary
    -0.08
    iato
    -0.07
     complimentary
    -0.07
    коми
    -0.06
    _MAPPING
    -0.06
    ält
    -0.06
    è¯ŃæĸĩæķĻåѦ
    -0.06
    åįľ
    -0.06
    ä¸ļåĬ¡å·¥ä½ľ
    -0.06
     behaviours
    -0.06
    POSITIVE LOGITS
    åħ¬å¼ı
    0.09
    计ç®Ĺåħ¬å¼ı
    0.09
    formula
    0.09
     formula
    0.09
     Formula
    0.09
     fórmula
    0.08
    usan
    0.08
    Formula
    0.08
    /Area
    0.08
    classname
    0.08
    Activations Density 0.095%

    No Known Activations