© 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. 44278
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
     Geb
    -0.07
    åħ¶æīĢ
    -0.06
    Âł
    -0.06
     compositions
    -0.06
    {}'.
    -0.06
    iry
    -0.06
    æĦŁçļĦ
    -0.06
    å¦Ĥæŀľä½¿çĶ¨
    -0.06
     xa
    -0.06
    èĥ½å¤ŁæĽ´å¥½åľ°
    -0.06
    POSITIVE LOGITS
    à¹īà¸ĩ
    0.08
     med
    0.07
    ++++
    0.07
    मत
    0.07
    entemente
    0.07
    egra
    0.07
    apore
    0.07
    æĺĨ
    0.07
    æºIJçłģ
    0.07
    awang
    0.07
    Activations Density 0.000%

    No Known Activations