© 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. 58947
    Prev
    Next
    INDEX
    Explanations

    introductions to lists or explanations

    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
    åı«ä»Ģä¹Ī
    -0.08
    åį³çĶ¨
    -0.08
     {}.
    -0.08
    åį³ä»¥
    -0.07
    åı«åģļ
    -0.07
     {}\
    -0.07
    idin
    -0.07
    nok
    -0.07
    çļĦä¸Ģç±»
    -0.07
    RA
    -0.07
    POSITIVE LOGITS
    )):
    0.07
     worth
    0.07
     mutu
    0.07
    _:
    0.07
    }):
    0.07
    éĢ¾
    0.07
    å½Ĵäºİ
    0.07
    ":"/
    0.06
    adrid
    0.06
     drown
    0.06
    Activations Density 0.105%

    No Known Activations