© 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. 26960
    Prev
    Next
    INDEX
    Explanations

    purchased manner portion

    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
    ter
    -0.10
    ation
    -0.09
    ìļĶ
    -0.08
    ness
    -0.07
    ence
    -0.07
    ÏĤ
    -0.07
    arr
    -0.07
    樣çļĦ
    -0.07
    ies
    -0.07
    féle
    -0.06
    POSITIVE LOGITS
    ر
    0.11
    à¹Ħà¸ĩ
    0.11
    Ö¼
    0.11
    à§įড
    0.10
    à¥į
    0.10
    edException
    0.09
    еÑĢÑĮ
    0.09
    ÑĩиÑĤа
    0.09
    ilien
    0.09
    ลฯ
    0.09
    Activations Density 0.814%

    No Known Activations