© 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. 16304
    Prev
    Next
    INDEX
    Explanations

    leads to

    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
    追æ±Ĥåįĵè¶Ĭ
    -0.08
     blindly
    -0.08
    ýt
    -0.07
    ggi
    -0.07
    æīĢå¤ĦçļĦ
    -0.07
     relentlessly
    -0.07
     zich
    -0.07
    ãģ¾ãģ¾ãģ§
    -0.07
     endeavour
    -0.07
    åģļä»»ä½ķ
    -0.07
    POSITIVE LOGITS
    æĢİæł·çļĦ
    0.10
     more
    0.09
     quicker
    0.08
     greater
    0.08
     clearer
    0.08
     clear
    0.08
    ä¸įäºĨ
    0.08
    ä¸Ģ个éĹ®é¢ĺ
    0.08
     ÙħزÙĬد
    0.08
     fewer
    0.07
    Activations Density 0.062%

    No Known Activations