© 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. 20471
    Prev
    Next
    INDEX
    Explanations

    other except one

    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
    pha
    -0.08
    araf
    -0.08
    anax
    -0.08
    åĴĮ第äºĮ
    -0.08
     hinter
    -0.08
    otch
    -0.08
    åıĤå·®ä¸įé½IJ
    -0.08
    etable
    -0.08
    åĨħéľĢ
    -0.08
    prog
    -0.07
    POSITIVE LOGITS
    æĺŃ
    0.07
     Schro
    0.06
    osten
    0.06
    åĸĢ
    0.06
    åħ±äº«
    0.06
    æ¸ħéĨĴ
    0.06
     ìĪľ
    0.06
    _helpers
    0.06
    ä¸Ģ声
    0.06
    ross
    0.06
    Activations Density 0.003%

    No Known Activations