© 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. 16848
    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
    ife
    -0.08
    åĽ½åįİ
    -0.08
    伯çī¹
    -0.08
    corev
    -0.07
    fej
    -0.07
    ingly
    -0.07
    razi
    -0.07
    otrop
    -0.07
    akin
    -0.07
    Smarty
    -0.07
    POSITIVE LOGITS
    好å¤ĦçļĦ
    0.06
     zeroes
    0.06
    为æİ¨è¿Ľ
    0.06
    ieur
    0.06
    ç¨ĭåºıä¸Ń
    0.06
     yht
    0.06
     associate
    0.06
    ucht
    0.06
    ieht
    0.06
    bsp
    0.06
    Activations Density 0.000%

    No Known Activations