© 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. 44866
    Prev
    Next
    INDEX
    Explanations

    hall effect, shift, exchange

    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
    tral
    -0.08
    etan
    -0.08
    inian
    -0.08
    isian
    -0.07
    enor
    -0.07
    æĭħ
    -0.07
    屡
    -0.07
    olvable
    -0.07
     à¹Ģศ
    -0.07
    èµİ
    -0.07
    POSITIVE LOGITS
    æĨ
    0.07
    [:]
    0.07
    -console
    0.07
     effect
    0.06
    åį«è®¡
    0.06
    æĬĢæľ¯åĴ¨è¯¢
    0.06
    åĭķ
    0.06
     ÑģоÑģÑĤавлÑı
    0.06
    æĺ¯çĶ±äºİ
    0.06
    æķĪåºĶ
    0.06
    Activations Density 0.002%

    No Known Activations