© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 18536
    Prev
    Next
    INDEX
    Explanations

    sequence terms

    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
    æİĪ课
    -0.07
    æľĽ
    -0.07
    æŃĮ
    -0.07
    enga
    -0.07
    红åĪ©
    -0.07
    è¹Ħ
    -0.07
    åĪĨä¸Ńå¿ĥ
    -0.07
    æķĺ
    -0.07
    å·¥ç¨ĭåĴĮ
    -0.07
    voke
    -0.06
    POSITIVE LOGITS
    zl
    0.08
    árd
    0.08
    OfClass
    0.08
     Mari
    0.07
     OU
    0.07
     ÑĢазве
    0.07
    ÛĮÙĨÙĩ
    0.06
    elpers
    0.06
    emers
    0.06
    äºı
    0.06
    Activations Density 0.026%

    No Known Activations