© 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. 58021
    Prev
    Next
    INDEX
    Explanations

    question beginning

    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
    awan
    -0.07
     decret
    -0.06
    oodles
    -0.06
    OfType
    -0.06
    çªŁ
    -0.06
    undles
    -0.06
    æĹłæĤĶ
    -0.06
    enerator
    -0.06
    agne
    -0.06
    adang
    -0.06
    POSITIVE LOGITS
    ä¸ĢåĽŀäºĭ
    0.12
    åĽŀäºĭ
    0.10
     caranya
    0.10
    对å¾ħ
    0.10
    /how
    0.10
    soever
    0.10
    во
    0.09
     ÙĪÙĥÙĬÙģ
    0.09
    мп
    0.09
    ä¸ĢæŃ¥æŃ¥
    0.09
    Activations Density 0.390%

    No Known Activations