© 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. 12328
    Prev
    Next
    INDEX
    Explanations

    going through a process

    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
    _extend
    -0.07
    stal
    -0.07
    çĿ¡è§ī
    -0.07
    teras
    -0.07
    åľ¨åı°
    -0.06
     боло
    -0.06
    eware
    -0.06
    åľ¨åħ¶ä»ĸ
    -0.06
    é£İ声
    -0.06
    ç»Łæ²»
    -0.06
    POSITIVE LOGITS
    åİĨç¨ĭ
    0.11
    è¿ĩç¨ĭ
    0.10
     process
    0.09
    è¿Ļ个è¿ĩç¨ĭ
    0.09
    ä¸ĢæŃ¥æŃ¥
    0.09
    è¿ĩç¨ĭçļĦ
    0.09
     steps
    0.09
     ê³¼ìłķìĿĦ
    0.09
     boyunca
    0.09
    åħ¨è¿ĩç¨ĭ
    0.08
    Activations Density 0.038%

    No Known Activations