© 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. 14377
    Prev
    Next
    INDEX
    Explanations

    lists of specific entities or topics

    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
    æ³ķå¾ĭ声æĺİ
    -0.08
    WithIdentifier
    -0.08
    åºĶè¿IJ
    -0.08
     */,
    -0.08
    ¤íĮ
    -0.08
    ÏĨοÏģά
    -0.08
    tent
    -0.08
    为æĤ¨æݨèįIJ
    -0.08
    reak
    -0.07
     (!((
    -0.07
    POSITIVE LOGITS
    å½¹
    0.06
    odie
    0.06
    /
    0.06
    Åį
    0.06
    бан
    0.06
    åĩīå±±
    0.06
    usi
    0.06
     pul
    0.06
    æĭĶ
    0.06
    æļij
    0.05
    Activations Density 0.425%

    No Known Activations