© 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. 43666
    Prev
    Next
    INDEX
    Explanations

    Swift code initialization

    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
    ertet
    -0.08
    ETA
    -0.08
    rey
    -0.07
    ä½ľä¸ºä¸Ģ个
    -0.07
    <decimal
    -0.07
    <cv
    -0.07
    åĦ¿çļĦ
    -0.07
    ector
    -0.07
    ette
    -0.06
    _VM
    -0.06
    POSITIVE LOGITS
    Siamo
    0.07
     (()
    0.07
     datings
    0.07
     penc
    0.07
     {};
    0.06
     kontra
    0.06
    erate
    0.06
    ä¾ĽåºĶ产åĵģ
    0.06
    æķ£çĻ¼
    0.06
    ?(
    0.06
    Activations Density 0.070%

    No Known Activations