© 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. 8492
    Prev
    Next
    INDEX
    Explanations

    Spice Routes

    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
     straight
    -0.07
     canlı
    -0.07
    åĺ»åĺ»
    -0.07
     رÙĪاÙĨ
    -0.07
    æĪIJæ´»
    -0.07
    å¥İ
    -0.07
    _REDIRECT
    -0.07
    æĮīçħ§è§Ħå®ļ
    -0.06
    arth
    -0.06
    çļĦä¸Ģåľº
    -0.06
    POSITIVE LOGITS
    idik
    0.07
    è´
    0.07
    ÙĦاÙħ
    0.07
    csrf
    0.07
    磨åIJĪ
    0.07
    Cached
    0.06
    ymar
    0.06
    å¿łå®ŀ
    0.06
    itters
    0.06
    åį´åĽłä¸º
    0.06
    Activations Density 0.002%

    No Known Activations