© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 694
    Prev
    Next
    INDEX
    Explanations

    similarly, likewise, or, sebaliknya

    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
    Negative Logits
    elia
    -0.07
    alah
    -0.07
    el
    -0.06
    åį´ä¸įæĺ¯
    -0.06
    arro
    -0.06
    stri
    -0.06
    ****
    -0.06
    Âł
    -0.06
    å®ī举
    -0.06
    elum
    -0.06
    POSITIVE LOGITS
     similarly
    0.11
    åıįä¹ĭ
    0.10
    åħ¶ä»ĸçļĦ
    0.10
    亦çĦ¶
    0.10
     likewise
    0.09
    çļĦåı¦ä¸Ģ
    0.09
     sebaliknya
    0.09
    APPER
    0.08
    Similarly
    0.08
    çļĦåħ¶ä»ĸ
    0.08
    Activations Density 0.056%

    No Known Activations