© 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. 58308
    Prev
    Next
    INDEX
    Explanations

    real numbers

    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
    aign
    -0.08
    коми
    -0.08
    illy
    -0.08
    ttp
    -0.08
    æĪijä»¬çĽ¸ä¿¡
    -0.07
     podp
    -0.07
    imore
    -0.07
     Bremer
    -0.07
    ä¸Ģç»ıåıijçİ°
    -0.07
    ÃŃcÃŃ
    -0.07
    POSITIVE LOGITS
    èĢĮä¸įæĺ¯
    0.06
    yata
    0.06
    ارÙĩ
    0.06
    容
    0.06
    æ±
    0.06
    峨çľī
    0.06
    ä¹İ
    0.06
     cr
    0.06
    æīĭ
    0.06
    ups
    0.06
    Activations Density 0.078%

    No Known Activations