© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 4556
    Prev
    Next
    INDEX
    Explanations

    date and time references

    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
    å½ĵ
    -0.06
    次年
    -0.06
    åľ¨å½ĵæŶ
    -0.06
    解ä½ĵ
    -0.06
    Misc
    -0.05
     ens
    -0.05
    uman
    -0.05
     F
    -0.05
    å½ĵå¹´
    -0.05
    ç³»
    -0.05
    POSITIVE LOGITS
    lott
    0.09
    apore
    0.09
    pora
    0.08
    pati
    0.08
    ä¸Ģå¸Ĩ
    0.08
    ấy
    0.08
    าà¸ĩ
    0.08
    主页
    0.08
    aukee
    0.08
    ç½ij绾æĬĢæľ¯
    0.08
    Activations Density 0.045%

    No Known Activations