© 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. 62526
    Prev
    Next
    INDEX
    Explanations

    reply indicating time or sender

    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
    {}
    -0.07
    æĿł
    -0.07
    {}]
    -0.06
    anci
    -0.06
    ami
    -0.06
    ongan
    -0.06
    è§ĦåĪĻ
    -0.06
    ×ķ×IJ
    -0.06
    aven
    -0.06
    ***
    -0.06
    POSITIVE LOGITS
     earlier
    0.10
     пÑĢедÑĭ
    0.09
     Earlier
    0.09
     poprzed
    0.08
     previous
    0.08
    æĹ©äºĽ
    0.08
    à¸ģà¹Īà¸Ńà¸Ļหà¸Ļà¹īาà¸Ļีà¹ī
    0.08
    åIJĮéģĵ
    0.08
     ÑĢанее
    0.07
    Earlier
    0.07
    Activations Density 0.291%

    No Known Activations