© 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. 12963
    Prev
    Next
    INDEX
    Explanations

    global, hub, mouth, zones, much, national

    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
    æľŁçļĦ
    -0.09
    zeit
    -0.09
    æľŁåĴĮ
    -0.09
    åĽŀ头
    -0.08
     onward
    -0.08
    æľŁ
    -0.08
    æľŁãģ®
    -0.08
    новÑĢемен
    -0.07
    ernity
    -0.07
    _DIRECTORY
    -0.07
    POSITIVE LOGITS
    singleton
    0.09
    åħ¬åı¸äºİ
    0.08
    /logger
    0.08
    å±ĬæŶ
    0.08
    omatik
    0.08
    itti
    0.07
    åľ¨è¿Ļ段æŶéĹ´
    0.07
    åĩĮ天
    0.07
    ilar
    0.07
    .jet
    0.07
    Activations Density 0.531%

    No Known Activations