© 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. 39546
    Prev
    Next
    INDEX
    Explanations

    preferably, possible

    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
    intis
    -0.08
     essentially
    -0.08
     presumably
    -0.08
    enor
    -0.08
    ivent
    -0.08
    istring
    -0.08
    боÑİ
    -0.08
    çIJĨ论ä¸Ĭ
    -0.07
     ÑıкобÑĭ
    -0.07
     arguably
    -0.07
    POSITIVE LOGITS
    æĥħåĨµä¸ĭ
    0.08
    ä¸įè¶ħè¿ĩ
    0.08
    erweise
    0.08
     sih
    0.08
    à¸Ńยà¹Īาà¸ĩยิà¹Īà¸ĩ
    0.08
    ä¹Łä¸įè¦ģ
    0.07
    Ùĭ
    0.07
    æľĢ好æĺ¯
    0.07
    ä¸įè¦ģçĶ¨
    0.07
    èĥ½çĶ¨
    0.07
    Activations Density 0.033%

    No Known Activations