© 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. 8042
    Prev
    Next
    INDEX
    Explanations

    special characters and placeholders

    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
    ¯
    -0.08
    ilate
    -0.07
    ä¸¥æł¼è¦ģæ±Ĥèĩªå·±
    -0.07
    вай
    -0.07
    berman
    -0.07
    à¸ģà¸Ńà¸ĩ
    -0.07
    리ê²Į
    -0.07
    коÑģ
    -0.07
    аÑĩ
    -0.07
     covid
    -0.06
    POSITIVE LOGITS
    éĩįçĤ¹åħ³æ³¨
    0.08
    æľºåħ³
    0.07
    ansa
    0.06
    aing
    0.06
    ело
    0.06
    åıĺæĽ´è®°å½ķ
    0.06
    ŃIJ
    0.06
    !*
    0.06
    çĿĢæĪijçļĦ
    0.06
    亮çļĦ
    0.06
    Activations Density 0.025%

    No Known Activations