© 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. 42093
    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
    ilik
    -0.08
    è¿ĺåĮħæĭ¬
    -0.07
     Erg
    -0.07
    Ø·ÙĨ
    -0.07
     آپ
    -0.07
    hung
    -0.07
    licit
    -0.07
    ibi
    -0.07
    èĬľ
    -0.07
     berh
    -0.07
    POSITIVE LOGITS
    ears
    0.07
    ÑĢем
    0.07
    鸣
    0.07
    akin
    0.07
    tu
    0.06
    akan
    0.06
    urm
    0.06
    cus
    0.06
    á»ĩu
    0.06
    оÑģÑĤа
    0.06
    Activations Density 0.000%

    No Known Activations