© 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. 4772
    Prev
    Next
    INDEX
    Explanations

    traffic signals and signs

    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
    离ä¸įå¼Ģ
    -0.06
    ä¸ľå±±
    -0.06
    é«ĺéĽħ
    -0.06
     loin
    -0.06
     copies
    -0.06
    åĽŀ访
    -0.06
    æĮ¯
    -0.06
    æŀķ
    -0.06
    å¾ĹåĬĽ
    -0.06
    寮
    -0.06
    POSITIVE LOGITS
    礼让
    0.10
    åı³è½¬
    0.09
    缴è¡Į
    0.09
     semaphore
    0.09
    绿çģ¯
    0.09
    延æŶ
    0.09
    æµģè¡Ģ
    0.09
     напÑĢа
    0.08
    signals
    0.08
    ebra
    0.08
    Activations Density 0.017%

    No Known Activations