© 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. 62836
    Prev
    Next
    INDEX
    Explanations

    initial stimuli

    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
    Ú¯ÛĮ
    -0.07
    åł
    -0.06
    طا
    -0.06
    åĹ
    -0.06
    oute
    -0.06
     Spi
    -0.06
    ordinal
    -0.06
    å¢
    -0.06
    {lng
    -0.06
    ì°©
    -0.06
    POSITIVE LOGITS
     inputs
    0.08
    èĬ¸
    0.08
    æºIJ
    0.08
    Gain
    0.08
    çĽĸ
    0.07
    -vector
    0.07
    queries
    0.07
    iette
    0.07
     portfolios
    0.07
    /vector
    0.07
    Activations Density 0.008%

    No Known Activations