© 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. 30605
    Prev
    Next
    INDEX
    Explanations

    cut-off thresholds or values

    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
    leftright
    -0.07
    styled
    -0.07
    临
    -0.06
    à¸Ĭัà¹īà¸Ļ
    -0.06
    .addElement
    -0.06
     آخرÛĮÙĨ
    -0.06
    临æŶ
    -0.06
    ä¸įæ¶īåıĬ
    -0.06
    æľĢæĸ°èµĦ讯
    -0.06
    uxt
    -0.06
    POSITIVE LOGITS
     signifies
    0.10
    indic
    0.10
    æķ°åĢ¼
    0.09
     indicating
    0.09
     indicates
    0.09
     thresholds
    0.09
     signify
    0.09
     Indicates
    0.09
     indicate
    0.08
     values
    0.08
    Activations Density 0.028%

    No Known Activations