© 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. 33471
    Prev
    Next
    INDEX
    Explanations

    equation delimiters

    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
    ){//
    -0.07
    _configuration
    -0.07
    æĥ³åĬŀæ³ķ
    -0.07
    гнÑĥ
    -0.07
    ",{
    -0.07
    ä¸įå¾Ĺä¸į
    -0.07
    новÑĢемен
    -0.07
    å¾ħåıij
    -0.07
    çľģå§Ķ常å§Ķ
    -0.07
    αιο
    -0.07
    POSITIVE LOGITS
    æµ®
    0.07
    ãģ®ãģĵãģ¨
    0.06
    æł©æł©
    0.06
    èݹ
    0.06
    ppy
    0.06
    以åıĬåľ¨
    0.06
    åı¶
    0.06
    aul
    0.06
    _UNDEFINED
    0.06
    èĤĨ
    0.06
    Activations Density 0.062%

    No Known Activations