© 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. 32717
    Prev
    Next
    INDEX
    Explanations

    large amounts

    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
    太é«ĺ
    -0.10
    wart
    -0.09
    çıĤ
    -0.09
    hofer
    -0.08
    è¶ĬæĿ¥è¶Ĭé«ĺ
    -0.08
    higher
    -0.08
     highest
    -0.08
    好好çļĦ
    -0.08
     higher
    -0.08
    highest
    -0.08
    POSITIVE LOGITS
    åºŀ大
    0.14
    åºŀ大çļĦ
    0.14
     vast
    0.11
     (>
    0.11
    é¾IJ
    0.11
    éĩıçļĦ
    0.11
    è§Ħ模
    0.10
    åŁºæķ°
    0.10
    -scale
    0.10
    éĩı大
    0.09
    Activations Density 0.340%

    No Known Activations