© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 26742
    Prev
    Next
    INDEX
    Explanations

    integration limits

    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
    çݺ
    -0.08
    çļĦ人è¿ĺ
    -0.07
    vertrag
    -0.07
    æĭĵ
    -0.07
    iele
    -0.07
    isis
    -0.07
    æĹłéĹ»
    -0.07
    æĬĹåĩ»
    -0.07
    èĦ
    -0.06
    Ïĥμα
    -0.06
    POSITIVE LOGITS
    бÑĢи
    0.08
    uen
    0.07
    ä¸įæĶ¹
    0.07
    åĵ©
    0.07
     оÑħо
    0.07
    bris
    0.07
    Pts
    0.07
    ujung
    0.07
    èĨ³
    0.07
    à¸Īุ
    0.06
    Activations Density 0.002%

    No Known Activations