© 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. 14320
    Prev
    Next
    INDEX
    Explanations

    biological entities and systems

    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¸Ģæķ°
    -0.09
    Ľ°
    -0.09
    æĹ¥ä»¥æĿ¥
    -0.08
    embalikan
    -0.08
    —who
    -0.08
    upeÅĤ
    -0.08
    ÐłÐŀÐĴ
    -0.08
    _plural
    -0.08
    duit
    -0.08
    permalink
    -0.08
    POSITIVE LOGITS
    ↵
    0.08
    elum
    0.06
     ...
    0.06
    ender
    0.06
    å½¹
    0.06
    ignal
    0.05
    æĪĸ
    0.05
     or
    0.05
    森
    0.05
    |
    0.05
    Activations Density 0.869%

    No Known Activations