© 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. 52201
    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
    ieber
    -0.08
    arka
    -0.08
    achine
    -0.08
    åłµè½¦
    -0.08
    icial
    -0.07
    èIJ½èĬ±
    -0.07
     Potr
    -0.07
    RATION
    -0.07
    åħŃåIJĪ
    -0.07
    lect
    -0.07
    POSITIVE LOGITS
    çĭ¬
    0.06
    im
    0.06
    çį¨
    0.06
    ym
    0.06
    iglio
    0.06
    ys
    0.06
     prox
    0.06
    imit
    0.06
     anyhow
    0.06
    å¥ĩæĢªçļĦ
    0.06
    Activations Density 0.000%

    No Known Activations