© 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. 16820
    Prev
    Next
    INDEX
    Explanations

    example numbers

    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
     "&#
    -0.07
     Eman
    -0.06
    anske
    -0.06
    euw
    -0.06
     prov
    -0.06
     userEmail
    -0.06
    дио
    -0.06
    ä½ĵåĬĽ
    -0.06
    æį¢è¨Ģä¹ĭ
    -0.06
    anes
    -0.06
    POSITIVE LOGITS
    aad
    0.08
    æł©
    0.07
    ä¹ĭä¸Ģæĺ¯
    0.07
    ×ĺ×Ļ
    0.07
    째
    0.07
    ieten
    0.07
    تÙħر
    0.07
    _working
    0.07
    åĩºå¥ĩ
    0.07
    /proto
    0.07
    Activations Density 0.140%

    No Known Activations