© 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. 23563
    Prev
    Next
    INDEX
    Explanations

    legal arguments and definitions

    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
    管çIJĨæĿ¡ä¾ĭ
    -0.08
    elines
    -0.07
    笨
    -0.06
    oroz
    -0.06
    çŃ¾å®ļ
    -0.06
    estra
    -0.06
    )$/
    -0.06
    nero
    -0.06
     SMB
    -0.06
     predefined
    -0.06
    POSITIVE LOGITS
    arguments
    0.11
    çIJĨ论çļĦ
    0.10
     arguments
    0.10
    论è¯ģ
    0.10
     debates
    0.09
     argument
    0.09
    åѸèĢħ
    0.09
     Argument
    0.09
    移æ¤į
    0.09
     proponents
    0.09
    Activations Density 0.005%

    No Known Activations