© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 62808
    Prev
    Next
    INDEX
    Explanations

    blog.blogspot.com

    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
    åĪ°æł¡
    -0.07
    aspers
    -0.07
    æİĪ
    -0.06
    é£ĺèį¡
    -0.06
    å¤ĸéĿ¢çļĦ
    -0.06
    _LS
    -0.06
    æĪĮ
    -0.06
    atti
    -0.06
    uns
    -0.06
    æĪĺ车
    -0.06
    POSITIVE LOGITS
    oland
    0.09
    eper
    0.08
    esser
    0.08
    tpl
    0.08
     DeepCopy
    0.08
    iris
    0.07
    icester
    0.07
    estival
    0.07
    estring
    0.07
    argin
    0.07
    Activations Density 0.020%

    No Known Activations