© 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. 14224
    Prev
    Next
    INDEX
    Explanations

    source or supply

    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
     TÆ°á»Ŀng
    -0.08
     mere
    -0.07
    isor
    -0.07
    áĢº
    -0.07
    å©ķ
    -0.06
    .extend
    -0.06
    ersions
    -0.06
    à¹Ĥà¸ķ
    -0.06
    ollar
    -0.06
    æĦıè¯Ĩ
    -0.06
    POSITIVE LOGITS
     source
    0.09
     sources
    0.09
     Sources
    0.09
    source
    0.09
    驱åĬ¨
    0.09
     اÙĦÙħصدر
    0.08
    .available
    0.08
     supply
    0.08
    åı¯ä¾Ľ
    0.08
     available
    0.08
    Activations Density 0.015%

    No Known Activations