© 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. 48423
    Prev
    Next
    INDEX
    Explanations

    light sources, OLEDs, modules, ration, Italy

    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
    ãģ§ä½ľ
    -0.07
    <strong
    -0.06
    æĺ¯ä¸Ģ家以
    -0.05
     ì¶ľìĭł
    -0.05
    (___
    -0.05
     ì¹ľìłĪ
    -0.05
     Sharia
    -0.05
    erdale
    -0.05
    è¡£èįī
    -0.05
    åĪĽå»ºäºİ
    -0.05
    POSITIVE LOGITS
    åĢ¼å¾ĹæľŁå¾ħ
    0.09
    /goto
    0.09
    æľªå®Įå¾ħç»Ń
    0.08
    æľĢç»ĪçļĦ
    0.08
    åĩ¤åĩ°ç½ij
    0.08
     Ultimately
    0.08
    биÑĤÑĮÑģÑı
    0.08
    argout
    0.08
    ä¸įäºĨå¤ļä¹ħ
    0.08
    æľĢç»Ī以
    0.08
    Activations Density 22.661%

    No Known Activations