© 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. 7933
    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
    olti
    -0.09
    ús
    -0.08
    otti
    -0.08
    ernos
    -0.07
    fare
    -0.07
    ÅĦczy
    -0.07
    æľ«é¡µ
    -0.07
    ÙĪتÙĬ
    -0.07
    ì²Ļ
    -0.07
    çį»
    -0.07
    POSITIVE LOGITS
    interop
    0.07
    å½Ĵ
    0.06
     provisional
    0.06
    enia
    0.06
    æĪª
    0.06
    èµ°åIJİ
    0.06
    åħ±åĪĨ
    0.06
    isté
    0.06
     else
    0.06
    æѸ
    0.06
    Activations Density 0.000%

    No Known Activations