© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 39785
    Prev
    Next
    INDEX
    Explanations

    option, trait, static, or fp

    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
    ascript
    -0.08
    ameni
    -0.08
    ุà¸Ķ
    -0.08
    Ø·ÙĬÙĨ
    -0.08
    æ°´åĮº
    -0.08
    æĸ¯é¡¿
    -0.08
    æĪijåĮº
    -0.08
    å°±æĺ¯æĪij们çļĦ
    -0.08
    {@
    -0.07
    çŃīèµĦæºIJ
    -0.07
    POSITIVE LOGITS
    åĬłæĮģ
    0.09
     flag
    0.09
    åĬłåĢį
    0.09
    æķĪæŀľ
    0.08
     modifier
    0.08
     added
    0.08
    _flag
    0.08
    _FLAG
    0.08
    表æĺİ
    0.08
    flag
    0.08
    Activations Density 0.145%

    No Known Activations