© 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. 59012
    Prev
    Next
    INDEX
    Explanations

    downhill or anabolic steroids

    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
    Ł
    -0.08
    å¤ĦçļĦ
    -0.08
    á»
    -0.07
    ä¸Ĭè¿Ľè¡Į
    -0.07
    ikal
    -0.07
    ä¸Ĭåģļ
    -0.07
    QueryString
    -0.07
    кви
    -0.07
    ä¸ĬæīĢ
    -0.07
    achel
    -0.07
    POSITIVE LOGITS
    æĢ§çĸ¾çĹħ
    0.08
    ulent
    0.08
    perienced
    0.07
    en
    0.07
    /down
    0.07
    atic
    0.07
    imity
    0.07
    åı¥åı¥
    0.06
    ectes
    0.06
    /-
    0.06
    Activations Density 0.002%

    No Known Activations