© 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. 30576
    Prev
    Next
    INDEX
    Explanations

    proper nouns and titles

    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
    æĦī
    -0.07
     appunto
    -0.07
    omma
    -0.06
     doomed
    -0.06
     jugg
    -0.06
    è¦ģæ±Ĥèĩªå·±
    -0.06
    ä¹ĭæķ°
    -0.06
    ould
    -0.06
     lied
    -0.06
    attes
    -0.06
    POSITIVE LOGITS
    éĻĦåĴĮ
    0.10
    é»ĺå¥ij
    0.08
    åıijè¨Ģ
    0.08
    èµŀåIJĮ
    0.08
    åľ¨æĹģè¾¹
    0.08
    çľĭ好
    0.08
    ä»ĸä»¬ä¹Ł
    0.07
    å·²ç»ıå°Ĩ
    0.07
    ä¸įä½ıçļĦ
    0.07
    ensing
    0.07
    Activations Density 0.065%

    No Known Activations