© 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. 50295
    Prev
    Next
    INDEX
    Explanations

    encoding or formatting separators

    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
    æľ¬ç«ĻåĨħ容
    -0.08
     suos
    -0.07
    гÑĢи
    -0.07
    éĢĤ
    -0.07
    macros
    -0.07
     aday
    -0.07
    /mac
    -0.07
    unya
    -0.07
    Thunder
    -0.06
    elsey
    -0.06
    POSITIVE LOGITS
    yer
    0.08
    aup
    0.07
    crc
    0.07
    ican
    0.07
    elÅij
    0.07
    efore
    0.07
    ÑģÑĮ
    0.07
    à®ļà¯įà®ļ
    0.07
     rip
    0.06
    å®īæİĴäºĨ
    0.06
    Activations Density 0.007%

    No Known Activations