© 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. 52207
    Prev
    Next
    INDEX
    Explanations

    comparing differences and similarity

    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
     Weinstein
    -0.08
    éĿĴåħī
    -0.08
    Danger
    -0.07
     Pej
    -0.07
    asic
    -0.07
     Dome
    -0.07
    æ¿
    -0.07
    écu
    -0.07
    amedi
    -0.07
    ä¿Ŀè¯ģåħ¶
    -0.07
    POSITIVE LOGITS
    çĽ¸ä¼¼åº¦
    0.10
     memcmp
    0.09
     diffs
    0.08
     differences
    0.08
    æ¯Ķ对
    0.08
     similarity
    0.08
    (diff
    0.08
     comparing
    0.08
     mismatch
    0.07
    çŁ¥å·±
    0.07
    Activations Density 0.059%

    No Known Activations