© 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. 50098
    Prev
    Next
    INDEX
    Explanations

    transistor 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
    eldes
    -0.08
    ਤà©ĩ
    -0.07
    çļĦç»ĦåIJĪ
    -0.07
    è¿ŀç»Ń
    -0.07
    æµ·éģĵ
    -0.07
    天æĺŁ
    -0.06
    ä¹Ŀä¹Ŀ
    -0.06
    å¤Ħ
    -0.06
    å¸ĥéĩĮ
    -0.06
    brace
    -0.06
    POSITIVE LOGITS
     whose
    0.17
    whose
    0.16
     cuyos
    0.13
     cuy
    0.13
     cuya
    0.11
     cuyo
    0.11
     dont
    0.10
    dont
    0.09
     cujo
    0.09
    èĢĮ以
    0.09
    Activations Density 0.464%

    No Known Activations