© 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. 30149
    Prev
    Next
    INDEX
    Explanations

    design, precision, impact, patterns

    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
     hopefully
    -0.07
     maybe
    -0.07
    åıªç®¡
    -0.07
    ån
    -0.07
    unks
    -0.07
    egative
    -0.06
    .ls
    -0.06
    anky
    -0.06
    uhe
    -0.06
    ellation
    -0.06
    POSITIVE LOGITS
    é¦ĸåħĪéľĢè¦ģ
    0.07
    便åĪ©ãģ§ãģĻ
    0.07
     fundamentally
    0.07
    鼶
    0.07
     полÑı
    0.07
    éĢĢ
    0.07
    ↵ ↵
    0.07
    æī®æ¼ĶçĿĢ
    0.07
    APT
    0.06
    é¦ĸåħĪåľ¨
    0.06
    Activations Density 0.001%

    No Known Activations