© 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. 31336
    Prev
    Next
    INDEX
    Explanations

    positioning and dimensions

    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
     gated
    -0.07
     strips
    -0.07
    软硬
    -0.06
     khép
    -0.06
    iram
    -0.06
    =all
    -0.06
    åħ¶ä¸ŃçļĦ
    -0.06
    atham
    -0.06
    è¿ŀç»ŃçļĦ
    -0.06
     strip
    -0.06
    POSITIVE LOGITS
    ä¸Ńå¿ĥ
    0.09
    åģı移
    0.09
    æ·Ģ
    0.09
    åIJĪéĢĤ
    0.08
     offsetof
    0.08
    lags
    0.08
     offset
    0.08
    olland
    0.08
    _offset
    0.07
     center
    0.07
    Activations Density 0.091%

    No Known Activations