© 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. 60339
    Prev
    Next
    INDEX
    Explanations

    only characters

    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
     loosely
    -0.07
    èches
    -0.07
    rawl
    -0.07
     definitions
    -0.07
    èĩªæĦ¿
    -0.06
    æķ´ä½ĵä¸Ĭ
    -0.06
    iid
    -0.06
    definitions
    -0.06
    è´´åIJ§
    -0.06
    æĭĸ
    -0.06
    POSITIVE LOGITS
    è¿Ļä¹Īç®Ģåįķ
    0.09
    åı¯ä»¥å¿«éĢŁ
    0.08
    å¿«éĢŁ
    0.08
    åħ¬å¼ı
    0.08
     formula
    0.08
    ãģķãģĪ
    0.07
     basta
    0.07
    èĥ½å¿«éĢŁ
    0.07
    olak
    0.07
    гелÑĮ
    0.07
    Activations Density 0.009%

    No Known Activations