© 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. 46862
    Prev
    Next
    INDEX
    Explanations

    MAX_TOKEN

    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
    éĢīæĭ©ä¸įåIJĮçļĦ
    -0.07
    åĽĽå¹³
    -0.06
    ail
    -0.06
    åıĪ说
    -0.06
    à¸ĸ
    -0.06
    ีà¹Īย
    -0.06
    ä¸įåı¯æĬĹ
    -0.06
    å¤ļä¹ħ
    -0.06
    IVA
    -0.06
    æĺ¯éĩĩçĶ¨
    -0.06
    POSITIVE LOGITS
    é¢Ħå¤ĩ
    0.08
    immel
    0.08
    ProductName
    0.07
    ারà§įথ
    0.07
    ardi
    0.07
     maxlen
    0.07
     Partie
    0.07
     Salvini
    0.07
    imax
    0.07
    eton
    0.07
    Activations Density 0.004%

    No Known Activations