© 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. 51253
    Prev
    Next
    INDEX
    Explanations

    names and suffixes

    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
    à¸ģาร
    -0.18
    à¸ģารà¸Ħà¹īà¸Ļหา
    -0.15
    à¸ģารà¹ģสà¸Ķà¸ĩ
    -0.14
    à¸ģารà¹Ģรียà¸Ļ
    -0.14
    à¸ģารสรà¹īาà¸ĩ
    -0.14
    æł·çļĦ
    -0.13
    à¸ģารà¸Īà¸Ńà¸ĩ
    -0.12
    voud
    -0.11
    ëį°
    -0.11
    à¸ģารà¸Ĺà¹Īà¸Ńà¸ĩà¹Ģà¸Ĺีà¹Īยว
    -0.11
    POSITIVE LOGITS
    s
    0.38
    ات
    0.30
    ãģĦãĤĭ
    0.23
    Ñĭ
    0.22
    schild
    0.19
    sche
    0.17
    sak
    0.17
    ska
    0.17
    ×Ļ×Ŀ
    0.17
    ske
    0.17
    Activations Density 5.216%

    No Known Activations