© 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. 61462
    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
    erver
    -0.08
    ä¸įçĶĺå¿ĥ
    -0.07
    quiz
    -0.07
    quen
    -0.07
    åĪ«
    -0.07
    onta
    -0.07
    .insert
    -0.06
    ahi
    -0.06
    uden
    -0.06
     Mete
    -0.06
    POSITIVE LOGITS
    bast
    0.08
    è£Ķ
    0.07
    ë£Į
    0.07
    äºĮåįģä¸Ģ
    0.07
    湧
    0.06
    ugal
    0.06
    ılım
    0.06
    ural
    0.06
    lak
    0.06
    velt
    0.06
    Activations Density 0.000%

    No Known Activations