© 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. 52066
    Prev
    Next
    INDEX
    Explanations

    technical or programming terms

    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
    Negative Logits
    åį´ä¾ĿçĦ¶
    -0.07
    ç½¹æĤ£
    -0.07
    eb
    -0.07
    -vers
    -0.06
    akit
    -0.06
    écie
    -0.06
     longtime
    -0.06
     nim
    -0.06
    åį´å§ĭç»Ī
    -0.06
    üz
    -0.06
    POSITIVE LOGITS
    æĢĿæĥ³ä¸Ĭ
    0.08
    å±±åºĦ
    0.08
    sung
    0.08
     %,
    0.07
    маÑģ
    0.07
    ìĬ¤íı¬
    0.07
    ongen
    0.07
    Ĥ¹
    0.07
    ÑĤник
    0.07
    çĮľä½łåĸľæ¬¢
    0.07
    Activations Density 0.002%

    No Known Activations