© 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. 19920
    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
    еÑĤе
    -0.08
    etto
    -0.08
    etta
    -0.07
    [at
    -0.07
    à¸Ńà¸ĩ
    -0.07
    esium
    -0.07
     ets
    -0.07
    ¹
    -0.07
    æĦ§
    -0.07
    olato
    -0.07
    POSITIVE LOGITS
    .Getenv
    0.08
    oris
    0.07
    ulls
    0.07
    HP
    0.07
    insky
    0.07
    ä¸ĬåĬł
    0.06
    ä¸Ģ亮
    0.06
    Cel
    0.06
    禧
    0.06
    ull
    0.06
    Activations Density 0.000%

    No Known Activations