© 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. 24565
    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
     Guth
    -0.08
    veld
    -0.08
    好çļĦ产åĵģ
    -0.07
    ijn
    -0.07
     krb
    -0.07
    ढ
    -0.07
    ãĤ¹ãĤ¿ãĤ¤
    -0.07
    好æĸĩ
    -0.07
     barring
    -0.06
    zell
    -0.06
    POSITIVE LOGITS
    aign
    0.07
    å®¡æł¸åIJİ
    0.07
    æĭĽèĤ¡
    0.07
     diá»ħn
    0.06
    çļĦç»ıéªĮ
    0.06
    -license
    0.06
    éĶµ
    0.06
    awah
    0.06
    adden
    0.06
    UNUSED
    0.06
    Activations Density 0.000%

    No Known Activations