© 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. 30200
    Prev
    Next
    INDEX
    Explanations

    special characters and symbols

    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
    ponsible
    -0.07
    blad
    -0.07
    _pub
    -0.07
     selectable
    -0.06
     tailored
    -0.06
    ÙĪÙĬب
    -0.06
    æĽ
    -0.06
    ç³»çļĦ
    -0.06
    umbling
    -0.06
    ç¼Ńç»ķ
    -0.06
    POSITIVE LOGITS
    aths
    0.07
    enda
    0.07
    åħ°
    0.07
    æ±ĤçĶŁåŃĺ
    0.07
    èĺŃ
    0.07
    å®īè¾¾
    0.07
    fér
    0.07
    ãģ¡ãģª
    0.07
    认è¯ģ
    0.07
    à¹Īาà¸Ļ
    0.07
    Activations Density 0.004%

    No Known Activations