© 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. 7306
    Prev
    Next
    INDEX
    Explanations

    punctuation and following clauses

    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
    éģĵ
    -0.08
    è²Į
    -0.07
    eldon
    -0.07
    æ®ĥ
    -0.07
    à¹īาย
    -0.07
     thù
    -0.07
    AGR
    -0.07
    éģĵ人
    -0.07
    UpdateTime
    -0.07
    adang
    -0.07
    POSITIVE LOGITS
    etje
    0.07
    è¦ģæ±Ĥåħ¶
    0.07
    bes
    0.07
    èĮĥæĸĩç½ij
    0.06
    zone
    0.06
    æ´Ĺ礼
    0.06
    editable
    0.06
    à¹Ģà¸Ķียวà¸ģัà¸ļ
    0.06
    à¸ļีà¹ī
    0.06
    æĦŁæŁĵäºĨ
    0.06
    Activations Density 0.312%

    No Known Activations