© 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. 57222
    Prev
    Next
    INDEX
    Explanations

    mathematical or special characters

    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
    çļĦ
    -0.11
    ìĿĦ
    -0.09
    åĴĮ
    -0.09
    zelfde
    -0.09
    ated
    -0.08
    raries
    -0.08
    ä¸Ń
    -0.08
    istic
    -0.07
    но
    -0.07
    สà¹Į
    -0.07
    POSITIVE LOGITS
    edException
    0.13
    ä½Ĩä¸įéĻIJäºİ
    0.10
    zeÅĽ
    0.09
    edImage
    0.09
     nél
    0.08
    canf
    0.08
    ables
    0.08
    etheus
    0.08
    ç»Ŀ伦
    0.08
    edList
    0.08
    Activations Density 0.027%

    No Known Activations