© 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. 9243
    Prev
    Next
    INDEX
    Explanations

    numbers and codes

    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
    èģĮä¸ļåѦéĻ¢
    -0.16
    à¹ĭ
    -0.10
    าว
    -0.10
    éĽĨä¸Ńæķ´æ²»
    -0.10
    ãĥªãĤª
    -0.09
    ä½łå¯¹è¿Ļ个åĽŀçŃĶçļĦè¯Ħä»·æĺ¯
    -0.09
    ìĹ°êµ¬ìĽIJ
    -0.09
    _OK
    -0.09
    á»ĩp
    -0.09
    รุ
    -0.09
    POSITIVE LOGITS
    _FAILURE
    0.11
    _SUCCESS
    0.10
    à¸Ķ
    0.10
    _ANY
    0.09
    วั
    0.09
    à¸Ļิà¸ķิ
    0.09
    à¹ģ
    0.08
    unga
    0.08
    à¹ĥà¸ļ
    0.07
    าร
    0.07
    Activations Density 2.459%

    No Known Activations