© 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. 52208
    Prev
    Next
    INDEX
    Explanations

    quantifiable metrics or status

    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
    æĬĬæīĢæľīçļĦ
    -0.08
    ported
    -0.08
    =center
    -0.08
    еÑĩ
    -0.08
    ë°ķ
    -0.07
    æµ·éģĵ
    -0.07
    ninger
    -0.07
    ICS
    -0.07
    çļĦèµĦæĸĻ
    -0.07
    èĮĥåĽ´ä¹ĭåĨħ
    -0.07
    POSITIVE LOGITS
    åıĬåħ¶
    0.07
    çĻ½ç¾Ĭ
    0.07
    æĿ¡
    0.07
    ONSE
    0.07
    ä¸ĢéĿ¢
    0.06
    éĶµ
    0.06
    ahari
    0.06
    æıIJ
    0.06
    å±Ĭ
    0.06
    _iface
    0.06
    Activations Density 0.018%

    No Known Activations