© 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. 44622
    Prev
    Next
    INDEX
    Explanations

    metabolite and progenies, radon, SPDX-License

    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
     deflate
    -0.08
    æ¯ĶåĪ«äºº
    -0.07
    è¾¹éĻħ
    -0.07
     taper
    -0.07
    meet
    -0.07
    æ¯Ķ以å¾Ģ
    -0.07
    ambu
    -0.06
     diagon
    -0.06
    ä¸İä»ĸ人
    -0.06
    æįį
    -0.06
    POSITIVE LOGITS
    éĵ¾
    0.10
    éĵIJ
    0.09
    -chain
    0.09
     NAMES
    0.09
    æľŁåĨħ
    0.09
     progen
    0.08
    _chain
    0.08
    names
    0.08
    Transient
    0.08
     transient
    0.08
    Activations Density 0.016%

    No Known Activations