© 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. 4645
    Prev
    Next
    INDEX
    Explanations

    we report

    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
     likewise
    -0.07
    严éĩįæŶ
    -0.07
     basically
    -0.07
    åįĥä¸ĩåĪ«
    -0.07
     furthermore
    -0.07
     thereof
    -0.07
    imuth
    -0.07
    ambo
    -0.07
    ä¹ŁåĽłæѤ
    -0.07
    ãģ¶ãĤĬ
    -0.07
    POSITIVE LOGITS
    对ä¸Ĭè¿°
    0.07
    èĤ´
    0.07
    ợ
    0.07
    macher
    0.07
    å°Ĩè¿Ļ
    0.07
    ilton
    0.07
    åģļä¸ĢåIJį
    0.07
    olars
    0.07
    tempts
    0.06
    otics
    0.06
    Activations Density 0.141%

    No Known Activations