© 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. 43062
    Prev
    Next
    INDEX
    Explanations

    approaching zero

    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
    æľ¬ç«ĻåĨħ容
    -0.09
    缺
    -0.08
    建æĪIJåIJİ
    -0.08
    artal
    -0.08
    γÏīγή
    -0.08
     Barcellona
    -0.08
    满满çļĦ
    -0.08
    agnol
    -0.08
    iw
    -0.08
    æĪIJåĬŁåIJİ
    -0.08
    POSITIVE LOGITS
     fin
    0.08
    è¶ĭäºİ
    0.08
     zero
    0.07
    æŃ¢
    0.07
    fin
    0.07
    ç£ĭ
    0.07
    鼶
    0.06
    éĴĿ
    0.06
    autom
    0.06
    鼶çĤ¹
    0.06
    Activations Density 0.005%

    No Known Activations