© 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. 25101
    Prev
    Next
    INDEX
    Explanations

    QCD

    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
    issen
    -0.08
    åĴĮè¦ģæ±Ĥ
    -0.08
    wohn
    -0.08
    ä¸Ģæī¹
    -0.07
    èħ°éħ¸
    -0.07
    riez
    -0.07
    phinx
    -0.07
    igd
    -0.07
    ENCY
    -0.07
    ÅŁe
    -0.07
    POSITIVE LOGITS
    -inspired
    0.09
    etic
    0.08
     interactions
    0.07
    assa
    0.07
    imir
    0.07
    .escape
    0.06
    浩çĢļ
    0.06
    Õ¡Õ¯Õ¡Õ¶
    0.06
     onRequest
    0.06
    èµĦè´¹
    0.06
    Activations Density 0.002%

    No Known Activations