© 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. 39880
    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
    à¹īม
    -0.07
    åIJŃ
    -0.07
     Dunk
    -0.07
    èī¯
    -0.07
    klı
    -0.06
    ä¸įåģľ
    -0.06
    模æĭŁèĢĥè¯ķ
    -0.06
     Falk
    -0.06
    .shadow
    -0.06
    Į¨
    -0.06
    POSITIVE LOGITS
    ÑĢани
    0.08
    oran
    0.08
    arend
    0.07
    rit
    0.07
    ấp
    0.07
    åıĪä¸Ģ个
    0.07
    åħ¨åĮħ
    0.07
    rend
    0.07
    acara
    0.07
    eschi
    0.07
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.