© 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. 63715
    Prev
    Next
    INDEX
    Explanations

    "Category:" or "Plus"

    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
     overt
    -0.07
    ä¸ĭåIJĮ
    -0.07
    ombang
    -0.07
    ä¸ĵæłıæĶ¶å½ķ该åĨħ容
    -0.07
    iations
    -0.06
    继èĢĮ
    -0.06
    使ä¹ĭ
    -0.06
    Inset
    -0.06
     reminiscent
    -0.06
     <!--[
    -0.06
    POSITIVE LOGITS
    0.09
    嬢
    0.08
    çĽ¸æľĽ
    0.07
     ARGS
    0.07
    etter
    0.07
    vere
    0.07
    umi
    0.07
    ³³³³³³³³
    0.07
    tera
    0.07
    ³³³³
    0.07
    Activations Density 0.009%

    No Known Activations