© 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. 7167
    Prev
    Next
    INDEX
    Explanations

    whether or not

    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
     accordingly
    -0.07
    æĬĬå®ĥ
    -0.07
    åĭĩå¾Ģ缴åīį
    -0.07
    ä»Ģä¹Īåij¢
    -0.07
    éĥ½å¸ĤæĬ¥
    -0.07
    è¿Ļå°±
    -0.06
    ãģĵãĤĮãĤĴ
    -0.06
     wors
    -0.06
    emm
    -0.06
    ç§ģæĪ¿
    -0.06
    POSITIVE LOGITS
    acson
    0.08
    æİĪæĿĥ使çĶ¨
    0.08
    ì¶Ķ
    0.07
    /how
    0.07
    çĤ¬
    0.07
    á»ĵng
    0.07
    коно
    0.06
     somehow
    0.06
    lessly
    0.06
    ijat
    0.06
    Activations Density 0.929%

    No Known Activations