© 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. 612
    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
    -0.07
    èĤ¢
    -0.06
    orgot
    -0.06
    鲸
    -0.06
    éģĩ
    -0.06
    jected
    -0.06
    ject
    -0.06
    Âł
    -0.06
    CAS
    -0.06
    ä¹ħåĿIJ
    -0.06
    POSITIVE LOGITS
    à¥įला
    0.08
    erto
    0.08
    (getClass
    0.08
    åħĭåĬĽ
    0.08
    yel
    0.08
    yers
    0.07
    éģĭ
    0.07
    æıŃå¹ķ
    0.07
    ertas
    0.07
    OfClass
    0.07
    Activations Density 0.000%

    No Known Activations