© 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. 39455
    Prev
    Next
    INDEX
    Explanations

    heard about

    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
     вплоÑĤÑĮ
    -0.07
     übrigens
    -0.07
    ailable
    -0.07
    odka
    -0.07
    anju
    -0.07
    PixelFormat
    -0.07
    AttributeName
    -0.07
    äºĭçĶ±
    -0.07
    och
    -0.06
    æľĢç»Ī
    -0.06
    POSITIVE LOGITS
     somewhere
    0.12
     somehow
    0.10
    æŁIJ个
    0.09
    æĬķèµĦæĪĸ
    0.08
    æŁIJåĢĭ
    0.08
     conflicting
    0.08
     alguna
    0.08
     alguno
    0.08
     irgend
    0.08
     algún
    0.08
    Activations Density 0.325%

    No Known Activations