© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 17286
    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
    èŃľ
    -0.09
    èı²å°Ķå¾·
    -0.08
     пÑĢеделÑĭ
    -0.08
    orges
    -0.08
    iegel
    -0.08
    å¦ĤæĹł
    -0.08
    .cd
    -0.08
    kert
    -0.08
    _UNIQUE
    -0.08
    ionato
    -0.08
    POSITIVE LOGITS
    ypy
    0.07
    all
    0.07
    es
    0.06
    æĦı
    0.06
    ä¸Ģå¾ĭ
    0.06
    è´¹çĶ¨çĶ±
    0.06
    haj
    0.06
     aiming
    0.06
    reb
    0.06
    #
    0.06
    Activations Density 0.000%

    No Known Activations