© 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. 2534
    Prev
    Next
    INDEX
    Explanations

    code comments or descriptions

    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
    ä»İæĹł
    -0.07
    '%(
    -0.07
     (_,
    -0.07
    èĢĮä¸Ĭ
    -0.07
    .Exists
    -0.07
    åIJİèĢħ
    -0.07
     ').
    -0.07
    _scal
    -0.07
    [url
    -0.07
    æĬĺ
    -0.07
    POSITIVE LOGITS
    åľ¨è¿ĻéĩĮ
    0.10
    è¿ĻéĩĮ
    0.09
    here
    0.09
    è¿ĻéĩĮæĺ¯
    0.09
     here
    0.09
     aqui
    0.08
    åĪ°è¿ĻéĩĮ
    0.08
     ÙĩÙĨا
    0.08
     ìĹ¬ê¸°ìĹIJ
    0.08
     здеÑģÑĮ
    0.08
    Activations Density 0.340%

    No Known Activations