© 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. 1657
    Prev
    Next
    INDEX
    Explanations

    simultaneous change

    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
    ctime
    -0.07
    IRE
    -0.07
    屡
    -0.06
    天çĽĸ
    -0.06
    ANY
    -0.06
    aj
    -0.06
    éĩ
    -0.06
    第äºĮ大
    -0.06
    åħĪçĶ¨
    -0.06
    éĴŀ
    -0.06
    POSITIVE LOGITS
    uzzi
    0.09
    ä¸İæѤåIJĮæŶ
    0.09
     compens
    0.09
     simultaneous
    0.08
     simultan
    0.08
     redistributed
    0.08
     simultaneously
    0.08
    对åħ¶ä»ĸ
    0.08
     realloc
    0.08
     ëıĻìĭľìĹIJ
    0.08
    Activations Density 0.065%

    No Known Activations