© 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. 17961
    Prev
    Next
    INDEX
    Explanations

    precisely, exactly, very

    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
    èĩªçĦ¶æĺ¯
    -0.08
     вообÑīе
    -0.08
     definitely
    -0.08
    å°±ç®ĹäºĨ
    -0.08
     addirittura
    -0.07
    èĩªçĦ¶ä¹Ł
    -0.07
     zelfs
    -0.07
    çĶļèĩ³æľī
    -0.07
    iglia
    -0.07
    å¿ħãģļ
    -0.07
    POSITIVE LOGITS
    æŃ£æĺ¯
    0.13
     itulah
    0.12
     inilah
    0.11
     ÙĩÙħÛĮÙĨ
    0.11
    è¿ĻæŃ£æĺ¯
    0.11
    æŃ£æĺ¯åľ¨
    0.10
    ä¹ŁæŃ£æĺ¯
    0.09
    æģ°æģ°
    0.09
    æģ°å¥½
    0.09
    ë°Ķë¡ľ
    0.08
    Activations Density 0.047%

    No Known Activations