© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 49434
    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
    Not in Any Lists

    No Comments

    Negative Logits
    Yep
    -0.08
     {!!
    -0.07
     Rodrig
    -0.07
    émon
    -0.07
    ypy
    -0.07
    kest
    -0.07
    missible
    -0.06
    asih
    -0.06
    la
    -0.06
    çļĦå½±åĵįåĬĽ
    -0.06
    POSITIVE LOGITS
    缸åħ³æݨèįIJ
    0.08
    irs
    0.07
    ndl
    0.07
    .extend
    0.07
     finally
    0.06
    bind
    0.06
    nings
    0.06
    å®Įæķ´çīĪ
    0.06
    åĪĿæŃ¥
    0.06
    æľŁ
    0.06
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.