© 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. 6998
    Prev
    Next
    INDEX
    Explanations

    self and `it` constructions

    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
    çļ®
    -0.07
    inheritDoc
    -0.06
    _lineno
    -0.06
    vip
    -0.06
    ÅĽÄĩ
    -0.06
    igin
    -0.06
    åħ¨ä½ĵ人åijĺ
    -0.06
    -env
    -0.06
    ÑįÑĤ
    -0.06
     impro
    -0.06
    POSITIVE LOGITS
    ä¾ĭå¦Ĥ
    0.27
    æ¯Ķå¦Ĥ
    0.24
    诸å¦Ĥ
    0.24
    èѬå¦Ĥ
    0.21
     ÐĿапÑĢимеÑĢ
    0.20
    ãģŁãģ¨ãģĪãģ°
    0.20
    ä¾ĭãģĪãģ°
    0.20
     напÑĢимеÑĢ
    0.19
     à¹Ģà¸Ĭà¹Īà¸Ļ
    0.19
     à¸Ńาà¸Ĺิ
    0.19
    Activations Density 0.431%

    No Known Activations