© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 19153
    Prev
    Next
    INDEX
    Explanations

    men and boys

    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
    کار
    -0.08
    åºĶçĶ¨åľ¨
    -0.08
     thứ
    -0.07
    fort
    -0.07
    æĺ¥ç¬ĭ
    -0.07
    лÑı
    -0.07
    åħ¶éģĵ
    -0.07
    zis
    -0.07
    hti
    -0.07
     Gér
    -0.07
    POSITIVE LOGITS
    éĻ¤å¤ĸ
    0.08
    以å¤ĸçļĦ
    0.07
    幸
    0.07
     Hom
    0.07
    æĢ
    0.06
    Mocks
    0.06
    ÓĻне
    0.06
     maupun
    0.06
    æĭī
    0.06
    æ´»
    0.06
    Activations Density 0.213%

    No Known Activations