© 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. 15910
    Prev
    Next
    INDEX
    Explanations

    introducing a category or explanation

    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
    æīĢ以对
    -0.09
    åIJĮä¸Ĭ
    -0.08
    éĤ£ä»ĸ
    -0.08
    æīĢ以ä»ĸ们
    -0.08
    æīĢ以她
    -0.07
    æīĢ以ä»ĸ
    -0.07
    then
    -0.07
     then
    -0.07
    çĦ¶åIJİçĤ¹åĩ»
    -0.07
    她åį´
    -0.07
    POSITIVE LOGITS
    è¶Ĭæĺ¯
    0.09
    ä¸Ģæĺ¯
    0.09
    ä¸Ģæĸ¹éĿ¢
    0.09
     afinal
    0.08
     although
    0.08
     namely
    0.08
    ledes
    0.07
    è¦ģéĢīæĭ©
    0.07
    è¦ģ让
    0.07
    è¦ģä¿Ŀè¯ģ
    0.07
    Activations Density 0.090%

    No Known Activations