© 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. 57300
    Prev
    Next
    INDEX
    Explanations

    numbers and units

    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
    è¾»
    -0.08
    antin
    -0.08
    ktop
    -0.08
    antum
    -0.08
    åħ¨çĽĺ
    -0.07
     meur
    -0.07
    utori
    -0.07
    å·´å·´
    -0.07
    à¸Īิ
    -0.07
    kert
    -0.07
    POSITIVE LOGITS
    0.06
    ä¹Ī
    0.06
    ä»İæĶ¿
    0.06
    ↵↵
    0.06
    è¾ĥå¥½åľ°
    0.06
    ÑģÑĤÑĢо
    0.06
    iegen
    0.06
    说ä¸Ģ说
    0.06
     Ende
    0.05
    æĺİå¾·
    0.05
    Activations Density 0.056%

    No Known Activations