© 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. 43668
    Prev
    Next
    INDEX
    Explanations

    code comments and programming operations

    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
    anja
    -0.08
    .yahoo
    -0.07
    ãĥ¬ãĥĥãĥĪ
    -0.07
    æĮ«
    -0.07
    ä¸ŃèĦ±é¢ĸèĢĮåĩº
    -0.07
    alsa
    -0.06
     interf
    -0.06
    å·²ç»ĵæĿŁ
    -0.06
    (/^\
    -0.06
     ì¹ĺ
    -0.06
    POSITIVE LOGITS
    æ°ı
    0.07
    ersp
    0.07
    以åħ¶
    0.07
    åĪ«è®©
    0.07
    rah
    0.07
    âm
    0.07
    æĹłæŶæĹłåĪ»
    0.07
    _unref
    0.07
    entin
    0.06
     refinement
    0.06
    Activations Density 0.004%

    No Known Activations