© 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. 2895
    Prev
    Next
    INDEX
    Explanations

    vice versa

    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
     neh
    -0.07
    .GetKey
    -0.07
    ä¸įæīĵ
    -0.07
    pires
    -0.07
    iales
    -0.07
    èĥĨåŃIJ
    -0.07
     ÐļÑĢаÑģи
    -0.07
    ä½łè¿ĺåľ¨
    -0.07
    çļĦå·¥ä½ľæĢģ度
    -0.07
    ä¸įçĶŁ
    -0.07
    POSITIVE LOGITS
    åıįè¿ĩæĿ¥
    0.16
     recip
    0.14
     reciprocal
    0.13
     vice
    0.13
     similarly
    0.13
    åıįä¹ĭ
    0.13
     recipro
    0.12
     reverse
    0.12
    亦çĦ¶
    0.11
    vice
    0.11
    Activations Density 0.088%

    No Known Activations