© 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. 63843
    Prev
    Next
    INDEX
    Explanations

    namely, which, or, such as, otherwise

    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
    ;
    -0.06
    ings
    -0.06
    并ä¸Ķ
    -0.06
    éric
    -0.06
    :
    -0.06
    isas
    -0.06
     —
    -0.06
    ç»Ļèĩªå·±
    -0.06
    éĤ£ä¹Īåľ¨
    -0.06
     sehingga
    -0.06
    POSITIVE LOGITS
     bagaim
    0.09
    顾åIJįæĢĿä¹ī
    0.08
     ÑĤоÑĩнее
    0.08
    è§ģæѤ
    0.08
    pite
    0.08
    ,is
    0.08
    )))),
    0.08
     _______,
    0.08
    maal
    0.08
     помимо
    0.07
    Activations Density 0.314%

    No Known Activations