© 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. 48078
    Prev
    Next
    INDEX
    Explanations

    single, one, two

    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
    æľīæīį
    -0.08
    润
    -0.07
    @\
    -0.07
    eos
    -0.07
    ValueType
    -0.07
    .flat
    -0.07
     ÑįÑĦи
    -0.07
    ä¸įèĥ½å®Įåħ¨
    -0.07
    ä¼°
    -0.07
    ä¸Ģå¤ķ
    -0.07
    POSITIVE LOGITS
     tunggal
    0.08
    à¸Ĺัศà¸Ļà¹Į
    0.08
    /single
    0.08
    Singleton
    0.07
    edly
    0.07
    è¡Į驶æŶ
    0.07
     Rapids
    0.07
    çĭ¬
    0.07
     Singleton
    0.07
     solo
    0.07
    Activations Density 0.004%

    No Known Activations