© 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. 59821
    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
    érie
    -0.08
    ืà¹īà¸Ńà¸ĩ
    -0.07
    uret
    -0.07
    iore
    -0.07
    IOC
    -0.07
    zaak
    -0.07
    ä¸įçĶ±
    -0.07
    åĪĨæŶ
    -0.07
    erings
    -0.07
    erk
    -0.07
    POSITIVE LOGITS
     Bals
    0.07
    Ł
    0.07
    å°ĭ
    0.06
    ord
    0.06
    inds
    0.06
    FX
    0.06
    èĵ¬
    0.06
    æī¬
    0.06
    CEE
    0.06
    aug
    0.06
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.