© 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. 45531
    Prev
    Next
    INDEX
    Explanations

    citations, code snippets, and specific sequences

    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
    obie
    -0.08
     basically
    -0.08
     Basically
    -0.07
     lately
    -0.07
    大æ¦Ĥæĺ¯
    -0.07
    bergen
    -0.07
    esz
    -0.07
    大æ¦Ĥ
    -0.07
    implicit
    -0.07
    obre
    -0.07
    POSITIVE LOGITS
    ä¾Ŀæ³ķ追究责任
    0.07
    该åĨħ容
    0.07
    æĢİä¹ĪäºĨ
    0.07
    æĪijå·²
    0.07
    é³
    0.06
    å·²äºİ
    0.06
    iap
    0.06
    çľĭéĢı
    0.06
    .isNull
    0.06
    åħ³å¿ĥåĴĮ
    0.06
    Activations Density 0.001%

    No Known Activations