© 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. 60024
    Prev
    Next
    INDEX
    Explanations

    inverse relationship

    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
    ä»İ头
    -0.08
    unde
    -0.07
    ä¸įå½Ĵ
    -0.07
    _forward
    -0.07
     Forward
    -0.06
    åѦéĻ¢éĻ¢éķ¿
    -0.06
    æľ¨åħ°
    -0.06
    resta
    -0.06
    igungen
    -0.06
    mento
    -0.06
    POSITIVE LOGITS
    åĴ²
    0.07
    è¶Ĭ大
    0.07
    ognito
    0.07
    è¶Ĭ好
    0.07
    è¶Ĭ
    0.07
    -ish
    0.07
    è¶Ĭå°ı
    0.07
    าม
    0.07
     اÙĦشدÙĬد
    0.07
    avad
    0.07
    Activations Density 0.012%

    No Known Activations