© 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. 21436
    Prev
    Next
    INDEX
    Explanations

    approximate values

    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
    oto
    -0.08
     Helf
    -0.07
     cle
    -0.07
    ÏĦζ
    -0.07
    orf
    -0.07
    æĸ¯åŁº
    -0.07
    åĨĻæĺİ
    -0.07
    iral
    -0.07
    æĭĽæīĭ
    -0.06
    ä¸įæĪIJ
    -0.06
    POSITIVE LOGITS
    è¿ijä¼¼
    0.10
     approximate
    0.10
     approx
    0.09
     пÑĢиблизиÑĤелÑĮно
    0.09
     slightly
    0.09
    çķ¥
    0.09
    éĿ¢ç§¯çº¦
    0.09
    PHONE
    0.09
    大æ¦Ĥåľ¨
    0.09
    _approx
    0.08
    Activations Density 0.001%

    No Known Activations