© 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. 51993
    Prev
    Next
    INDEX
    Explanations

    function, number, batches, memory, variables

    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
    chner
    -0.08
    è¿Ļæĸ¹éĿ¢
    -0.08
    对ä¸Ĭè¿°
    -0.07
    ä»İè¿Ļ个
    -0.07
    åľ¨è¿Ļæĸ¹éĿ¢
    -0.07
    çĥŃæĴŃ
    -0.07
    enschaft
    -0.07
    ymous
    -0.07
     rather
    -0.07
    å¦Ĥä¸Ĭ
    -0.07
    POSITIVE LOGITS
    ัส
    0.07
     whisper
    0.07
    åı¯ä»¥æł¹æį®
    0.07
    jun
    0.07
    æł¹æį®åĽ½å®¶
    0.06
    cola
    0.06
    Sen
    0.06
    heus
    0.06
    åĭģ
    0.06
    åı¯ä»¥æĮīçħ§
    0.06
    Activations Density 0.090%

    No Known Activations