© 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. 28961
    Prev
    Next
    INDEX
    Explanations

    `define` or `cin`

    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
    edException
    -0.08
    hood
    -0.08
    entimes
    -0.08
    çĽijå±Ģ
    -0.07
    inality
    -0.07
    kej
    -0.07
    лайн
    -0.07
    escaping
    -0.07
    RTOS
    -0.07
    ttes
    -0.07
    POSITIVE LOGITS
    ÙĪاÙħ
    0.09
    åĴĮé£İ
    0.07
    elmi
    0.07
     plain
    0.06
    _CAPTURE
    0.06
     IGNORE
    0.06
    _ws
    0.06
    ufer
    0.06
    ä¹ĭäºİ
    0.06
    ä¹ĭå¤ľ
    0.06
    Activations Density 0.001%

    No Known Activations