© 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. 3345
    Prev
    Next
    INDEX
    Explanations

    algorithm, suspected

    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
    å®ĺåı¸
    -0.07
    æĺķ
    -0.07
    ä¸Ģæĭį
    -0.07
     Giac
    -0.07
    ience
    -0.07
     breakdown
    -0.06
    å¹³æŶçļĦ
    -0.06
    Compatibility
    -0.06
    esion
    -0.06
    åŀ«ä»ĺ
    -0.06
    POSITIVE LOGITS
    ç®Ĺæ³ķ
    0.08
    algorithm
    0.08
     ash
    0.08
    èį¡
    0.07
    æ·ĺæ±°
    0.07
    æľ¬æ³ķ
    0.07
    ä¼łæĴŃ
    0.07
    åĩ¡
    0.07
    æİĪ
    0.07
     algorit
    0.07
    Activations Density 0.002%

    No Known Activations