© 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. 656
    Prev
    Next
    INDEX
    Explanations

    buyang huanwu

    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
    uens
    -0.06
    èĬ¸
    -0.06
    å´İå¸Ĥ
    -0.06
    ä¸Ģç¬ij
    -0.06
    ä¸Ģ个æĺ¯
    -0.06
    merk
    -0.06
    åķĨçļĦ
    -0.06
    åĵ¥çļĦ
    -0.06
    edar
    -0.06
    inkel
    -0.06
    POSITIVE LOGITS
    çŁ£
    0.10
    ä¸ī个åŃĹ
    0.09
    åħ®
    0.09
    ä¸īåŃĹ
    0.09
    å¿Ĺæĺİ
    0.08
    aat
    0.08
    ä¸Ĭæ·»
    0.08
    itions
    0.07
    å¢ĥ
    0.07
    çķĶ
    0.07
    Activations Density 0.030%

    No Known Activations