© 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. 13242
    Prev
    Next
    INDEX
    Explanations

    numbers or mathematical expressions

    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
    çļĦå¿ĥæĢĿ
    -0.07
    æĢĢåŃķæľŁéĹ´
    -0.07
    anton
    -0.07
     preen
    -0.06
     کرÙĨ
    -0.06
    -gnu
    -0.06
    æĹ©
    -0.06
    osaur
    -0.06
    ìĤ
    -0.06
    æĹ©åıijçİ°
    -0.06
    POSITIVE LOGITS
    åĪ«
    0.08
    à¹Ģà¸Ľà¹ĩà¸Ļà¸Ńยà¹Īาà¸ĩ
    0.07
    ë§Īëĭ¤
    0.07
    uris
    0.07
    Helpers
    0.07
    ä¸Ģä½ĵçļĦ
    0.07
    ãĢħãģ®
    0.07
    -highlight
    0.06
    个ä½ĵçļĦ
    0.06
    ichte
    0.06
    Activations Density 0.006%

    No Known Activations