© 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. 55225
    Prev
    Next
    INDEX
    Explanations

    inclusion

    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
    é¦ĸéĢī
    -0.08
    å¾Ĺä¸Ģ
    -0.07
    _LONG
    -0.07
    Preference
    -0.07
    мени
    -0.06
    åħ³éĶ®çݯèĬĤ
    -0.06
    à¸Ľà¸£à¸´
    -0.06
     Preference
    -0.06
     preferred
    -0.06
    ahul
    -0.06
    POSITIVE LOGITS
     inclusion
    0.10
    Included
    0.09
    åĵªäºĽ
    0.09
     INCLUDED
    0.09
     вклÑİÑĩениÑı
    0.09
    åĩ¡æĺ¯
    0.08
    æĥ³äºĨæĥ³
    0.08
    åħ¨éĢī
    0.08
     included
    0.08
     inclu
    0.08
    Activations Density 0.001%

    No Known Activations