© 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. 9360
    Prev
    Next
    INDEX
    Explanations

    browser named

    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
    orgen
    -0.07
    èĭ¥æĺ¯
    -0.07
    óc
    -0.06
     usually
    -0.06
    uló
    -0.06
     LAV
    -0.06
    dj
    -0.06
    æĭ¥æľī丰å¯ĮçļĦ
    -0.06
    úm
    -0.06
    oglie
    -0.06
    POSITIVE LOGITS
    -win
    0.07
     "@"
    0.07
    æĸĩç«łæłĩçŃ¾
    0.07
    éĤ£ä¹Īç®Ģåįķ
    0.07
    è¿Ļä¹Īä¹ħ
    0.07
    çī¹æѤ
    0.07
    以ä¸ĭç®Ģ称
    0.07
     Pfeffer
    0.07
    èī²åĪĹ
    0.07
    omber
    0.07
    Activations Density 0.017%

    No Known Activations