© 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. 7175
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions with numbers

    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
    à¹īà¸Ńย
    -0.09
    ÙĦاÙĦ
    -0.08
    äck
    -0.08
    zburg
    -0.08
    oule
    -0.08
    æĬķ稿éĤ®ç®±
    -0.07
    óle
    -0.07
    orti
    -0.07
    çħī
    -0.07
    åĤ»äºĨ
    -0.07
    POSITIVE LOGITS
    éºŁ
    0.08
    è§
    0.07
    idget
    0.06
    è¿ŀæİ¥æľī
    0.06
    undy
    0.06
     Yus
    0.06
    yu
    0.06
     Rao
    0.06
    åıĬ个人
    0.06
     cue
    0.06
    Activations Density 0.003%

    No Known Activations