© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 22841
    Prev
    Next
    INDEX
    Explanations

    actual expected possible values

    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
    çļĦçī¹çĤ¹æĺ¯
    -0.07
    èݱæĸ¯
    -0.07
     aÃŃ
    -0.07
    uze
    -0.07
    NCY
    -0.07
    irected
    -0.07
    æĹłä»¥
    -0.07
    auga
    -0.07
    åĽ¾çīĩç´łæĿIJ
    -0.06
    .defaults
    -0.06
    POSITIVE LOGITS
     desired
    0.09
     actual
    0.08
    åºĶæī¿æĭħ
    0.08
     ÑıкобÑĭ
    0.08
     tolerated
    0.08
     اÙĦÙħØ·ÙĦÙĪب
    0.07
    åĮĸäºĨ
    0.07
     expected
    0.07
     possible
    0.07
    åīįåºĶ
    0.07
    Activations Density 0.041%

    No Known Activations