© 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. 49124
    Prev
    Next
    INDEX
    Explanations

    grew again

    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
    çĬ¯çļĦ
    -0.08
    bab
    -0.08
    elta
    -0.08
    çĬ¯äºĨ
    -0.08
    betes
    -0.08
    à¹Ģà¸Ĥà¹ĩม
    -0.08
    åħ±åĴĮåĽ½
    -0.08
    æĪijçļĦ人
    -0.08
    åĨį以
    -0.08
    交çļĦ
    -0.08
    POSITIVE LOGITS
     specifically
    0.07
    æ±¾
    0.07
     promptly
    0.06
     presently
    0.06
     satisfactory
    0.06
     specially
    0.06
    æĭ¼
    0.06
    ooth
    0.06
     **
    0.06
    lah
    0.06
    Activations Density 0.003%

    No Known Activations