© 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. 26252
    Prev
    Next
    INDEX
    Explanations

    thresholds, onset, and yield points

    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
    åѦçļĦ
    -0.07
    _WS
    -0.07
    ych
    -0.07
    زÛĮ
    -0.07
    çłĶ
    -0.06
    atics
    -0.06
     cavo
    -0.06
    zo
    -0.06
    èĩ´çļĦ
    -0.06
    山顶
    -0.06
    POSITIVE LOGITS
    à¹Ģà¸Ķà¸Ĭ
    0.08
    ئÙĨ
    0.07
    less
    0.07
    etect
    0.07
    lessness
    0.07
    byname
    0.07
    mark
    0.07
     criterion
    0.07
    _ALREADY
    0.07
    iefer
    0.06
    Activations Density 0.001%

    No Known Activations