© 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. 28113
    Prev
    Next
    INDEX
    Explanations

    names from academic texts

    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
    äºijå±±
    -0.07
    å½ĵ羣
    -0.07
    sla
    -0.07
    vement
    -0.07
    貫
    -0.07
    é¾Ļå±±
    -0.06
     tan
    -0.06
    Ïĥή
    -0.06
    {})
    -0.06
    amoto
    -0.06
    POSITIVE LOGITS
    åı¤ä»Ĭ
    0.08
    æķĻç§ij
    0.08
    ikers
    0.08
    iku
    0.07
    icka
    0.07
    ngu
    0.07
    年代
    0.07
    abcd
    0.07
    西åŁİ
    0.07
    grad
    0.07
    Activations Density 0.030%

    No Known Activations