© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 65451
    Prev
    Next
    INDEX
    Explanations

    new beginnings or advancements

    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
    nieuw
    -0.08
    /il
    -0.08
    tober
    -0.08
    çļĦåħ¨éĥ¨åĨħ容
    -0.08
    åİĨéĻ©
    -0.08
    림
    -0.08
    اردة
    -0.07
     empl
    -0.07
    fts
    -0.07
    letic
    -0.07
    POSITIVE LOGITS
     early
    0.09
     recently
    0.08
     decades
    0.08
    以æĿ¥
    0.08
     modern
    0.08
    è¿ijå¹´æĿ¥
    0.08
    ä¸įä¹ħ
    0.07
    ä¸Ĭä¸ĸ纪
    0.07
     revolution
    0.07
     recent
    0.07
    Activations Density 1.638%

    No Known Activations