© 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. 57410
    Prev
    Next
    INDEX
    Explanations

    ages and life stages

    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
    溢
    -0.08
    æ¼Ĥ
    -0.07
     margin
    -0.07
     ìĿµ
    -0.07
    ãĥªãĤ¨
    -0.07
     rebound
    -0.07
     bay
    -0.07
    vic
    -0.06
     Lik
    -0.06
    .float
    -0.06
    POSITIVE LOGITS
    enger
    0.08
    isode
    0.08
     communiqué
    0.07
     gcd
    0.07
    ensburg
    0.07
    å®ĺæĸ¹åįļ客
    0.07
    gcd
    0.07
    çłº
    0.07
    çŁ¿
    0.07
    à¹ģà¸ĸ
    0.07
    Activations Density 0.003%

    No Known Activations