© 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. 24378
    Prev
    Next
    INDEX
    Explanations

    earliest occurrence or origin

    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
    åī©ä¸ĭ
    -0.08
    å¿ħè¦ģæŶ
    -0.07
    exas
    -0.07
     bakar
    -0.07
    ä½³èĤ´
    -0.07
     rež
    -0.07
    è¿IJ
    -0.07
    å¹³æŶ
    -0.06
     unterwegs
    -0.06
    θα
    -0.06
    POSITIVE LOGITS
    æľĢæĹ©çļĦ
    0.12
     earliest
    0.10
    ä¸įæĹ©
    0.09
    æľĢæĹ©
    0.09
     proto
    0.09
    é¦ĸä¾ĭ
    0.09
    éĽıå½¢
    0.08
    åİŁåŀĭ
    0.08
    èIJĮèĬ½
    0.08
     má»ijc
    0.08
    Activations Density 0.162%

    No Known Activations