© 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. 39133
    Prev
    Next
    INDEX
    Explanations

    transistor on/off operation

    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
    éĢĴ
    -0.07
    ult
    -0.07
     Torn
    -0.07
     scrolled
    -0.06
    çļĦæĪIJåĬŁ
    -0.06
    åıijçĹħçİĩ
    -0.06
    caps
    -0.06
    inery
    -0.06
    æĪĸå¤ļ个
    -0.06
    丰åİ¿
    -0.06
    POSITIVE LOGITS
    å·¥ä½ľçĬ¶æĢģ
    0.08
    ä¸ĭä¸Ģéĺ¶æ®µ
    0.08
    liz
    0.08
    éĥ½å¤Ħäºİ
    0.07
    éĺ¶
    0.07
    æĿ¡ä»¶æĺ¯
    0.07
    çĬ¶æĢģçļĦ
    0.07
     ë²Ĺìĸ´ëĤĺ
    0.07
     conditions
    0.07
     regime
    0.07
    Activations Density 0.002%

    No Known Activations