© 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. 64743
    Prev
    Next
    INDEX
    Explanations

    next followed by progression indicator

    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
    èĩªåı¤
    -0.09
    åIJİæľŁ
    -0.09
    æĻļæľŁ
    -0.08
     previo
    -0.08
     lately
    -0.08
    è¿ijäºĽå¹´
    -0.08
    alb
    -0.08
    isht
    -0.08
    æľĢç»Ī以
    -0.08
    æĹ©å¹´
    -0.08
    POSITIVE LOGITS
    ,next
    0.14
     next
    0.14
    ä¸ĭä¸Ģ个
    0.13
    (next
    0.13
    next
    0.13
    ç´§æİ¥çĿĢ
    0.12
    -next
    0.12
    ä¸ĭä¸Ģ
    0.11
    .next
    0.11
    æİ¥çĿĢ
    0.11
    Activations Density 0.101%

    No Known Activations