© 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. 25073
    Prev
    Next
    INDEX
    Explanations

    solutions to problems

    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
    设为
    -0.07
    tern
    -0.07
    à¸ģารà¹ĥà¸Ĭà¹ī
    -0.07
    eam
    -0.07
    éľĢè¦ģçĶ¨
    -0.06
    ç»ĻäºĨæĪij们
    -0.06
    æĻŁ
    -0.06
    Allows
    -0.06
    表çݰ为
    -0.06
     usar
    -0.06
    POSITIVE LOGITS
    æ¶ĪéĻ¤
    0.10
    idor
    0.10
    åĩıå°ij
    0.08
    ç»´æĬ¤åĴĮ
    0.08
    ä»İæł¹æľ¬ä¸Ĭ
    0.08
    åİ»éĻ¤
    0.08
    å¼¥
    0.08
    ç»´æĬ¤
    0.08
    涤
    0.08
    éĺ²æŃ¢
    0.08
    Activations Density 0.475%

    No Known Activations