© 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. 59890
    Prev
    Next
    INDEX
    Explanations

    codes and expiration

    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
     rapp
    -0.07
    otra
    -0.07
    次éĺħ读
    -0.07
    prs
    -0.06
    èĵĿèī²åŃĹä½ĵ
    -0.06
    اة
    -0.06
     méd
    -0.06
    åħįè´¹åıijå¸ĥ
    -0.06
    itech
    -0.06
    éĩĩ
    -0.06
    POSITIVE LOGITS
    çļĦè¿Ļç§į
    0.08
    å°±è¿Ļä¹Ī
    0.07
    å°±è¿Ļæł·
    0.07
    ä¸ĢåĽ¾
    0.07
    ä¸Ģåĩ»
    0.07
    0.07
    fter
    0.07
    :not
    0.07
    ä¸į误
    0.06
    å°±éĢĻ樣
    0.06
    Activations Density 0.016%

    No Known Activations