© 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. 34920
    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
    ä¾Ľ
    -0.06
    å°±åľ°
    -0.06
    inte
    -0.06
    ement
    -0.06
    åĪ¶èį¯æľīéĻIJåħ¬åı¸
    -0.06
    å½ĵäºĭ
    -0.06
    Robot
    -0.06
    vj
    -0.06
    रà¥ĭ
    -0.06
    MM
    -0.06
    POSITIVE LOGITS
    å³
    0.08
    ycl
    0.07
    avic
    0.07
    kena
    0.07
    åĴ«å°º
    0.07
     Rebellion
    0.07
     inclus
    0.07
    å¿įä½ı
    0.07
    æµģè¿ŀ
    0.07
    akis
    0.07
    Activations Density 0.000%

    No Known Activations