© 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. 24782
    Prev
    Next
    INDEX
    Explanations

    math expressions or calculations

    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
    Keys
    -0.06
    epen
    -0.06
    åľĨæĺİ
    -0.06
    inium
    -0.06
    addon
    -0.06
     replicated
    -0.06
    ropolit
    -0.06
    ä½Ĩ并ä¸į
    -0.06
    صÙĪرة
    -0.06
    urgo
    -0.06
    POSITIVE LOGITS
    æłĩåĩĨ为
    0.08
    æłĩåĩĨè¦ģæ±Ĥ
    0.08
    åĬ¨è¾Ħ
    0.07
    isspace
    0.07
    å®ļä¹ī为
    0.07
    ç»Ļå®Ŀå®Ŀ
    0.07
    .freeze
    0.07
    ä¸ĢéĹ®
    0.07
    åį³åı¯æŁ¥çľĭ
    0.07
    .TryParse
    0.07
    Activations Density 0.004%

    No Known Activations