© 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. 23888
    Prev
    Next
    INDEX
    Explanations

    parameters, fields, and data types

    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
    CursorPosition
    -0.08
    _INTERRUPT
    -0.08
    åįĹå±±
    -0.07
    "]/
    -0.07
     norwegian
    -0.07
    engar
    -0.07
    endale
    -0.07
    []=
    -0.07
    (scroll
    -0.06
    adia
    -0.06
    POSITIVE LOGITS
     saper
    0.07
    åĽ°éļ¾åĴĮéĹ®é¢ĺ
    0.07
     feas
    0.07
     Kolleg
    0.06
     unreasonable
    0.06
    Uploaded
    0.06
    çľĭå¾Ĺè§ģ
    0.06
    èĤīçľ¼
    0.06
    y
    0.06
     existed
    0.06
    Activations Density 0.003%

    No Known Activations