© 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. 37911
    Prev
    Next
    INDEX
    Explanations

    IR Group

    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
    بات
    -0.07
    åįĥåįĥ
    -0.07
    ä¼ģä¸ļåıĬ
    -0.07
    æĬ½æIJIJ
    -0.07
     trÃłng
    -0.07
    juta
    -0.07
    ocie
    -0.07
    设计åıĬ
    -0.06
    æĥħåĨµåıĬ
    -0.06
    jer
    -0.06
    POSITIVE LOGITS
    \"
    0.08
    ersh
    0.07
    çŃł
    0.07
    å°ıå°ıçļĦ
    0.07
    eve
    0.07
    ummer
    0.07
    umer
    0.07
    -dev
    0.06
    æĨ¬
    0.06
    ä¸ĢçĤ¹ä¸Ģæ»´
    0.06
    Activations Density 0.032%

    No Known Activations