© 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. 59006
    Prev
    Next
    INDEX
    Explanations

    air condition / conditioning

    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
    jenigen
    -0.08
     Setia
    -0.08
    å§Ķ书记
    -0.08
    ลฯ
    -0.08
    oriously
    -0.08
    ever
    -0.08
    رة
    -0.07
    ï¸ı
    -0.07
    æĤ¨åı¯èĥ½
    -0.07
    ÑģÑĤÑĮÑİ
    -0.07
    POSITIVE LOGITS
    borne
    0.09
    foil
    0.09
    åĴĮæ°´
    0.09
    worm
    0.08
    ضا
    0.08
    bnb
    0.08
    ways
    0.08
    بطاÙĦ
    0.08
    lessness
    0.07
    æĢ»ç½²
    0.07
    Activations Density 0.043%

    No Known Activations