© 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. 55923
    Prev
    Next
    INDEX
    Explanations

    technical terms in specific contexts

    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
    ulli
    -0.08
    æŶæŶ
    -0.07
    -fire
    -0.07
     дÑĢÑĥг
    -0.07
    egel
    -0.07
    orses
    -0.06
    æĻļä¸Ĭ
    -0.06
    å½ĵä¸Ń
    -0.06
     hopefully
    -0.06
    ported
    -0.06
    POSITIVE LOGITS
     deliberately
    0.08
     altså
    0.08
     plainly
    0.08
     analogue
    0.07
    åIJįåī¯åħ¶å®ŀçļĦ
    0.07
    czy
    0.07
    æĹ¢èĥ½
    0.07
     intentionally
    0.07
    ’s
    0.07
    ¾
    0.06
    Activations Density 0.003%

    No Known Activations