© 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. 48437
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions with parentheses

    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
    ×Ļף
    -0.09
    æł¹æį®æĿĥåĪ©è¦ģæ±Ĥ
    -0.08
    éķ°
    -0.08
     طبÙĤ
    -0.07
    ftware
    -0.07
    ุย
    -0.07
    noten
    -0.07
    åĿĬ
    -0.07
    dcc
    -0.07
    GroupName
    -0.07
    POSITIVE LOGITS
    åħ¶éģĵ
    0.07
    зеÑĢ
    0.06
    à¹ģà¸Ļ
    0.06
     tem
    0.06
    ermo
    0.06
    åĦª
    0.06
    (cols
    0.06
    Cols
    0.06
    TEM
    0.06
    caler
    0.06
    Activations Density 0.003%

    No Known Activations