© 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. 31881
    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
    裳
    -0.07
    reti
    -0.07
    stitu
    -0.07
    æĹłåIJį
    -0.07
    éĶħ
    -0.07
     ÐIJнÑĤо
    -0.07
    èİ«
    -0.06
    uters
    -0.06
    ikli
    -0.06
    fé
    -0.06
    POSITIVE LOGITS
    bacher
    0.08
    rompt
    0.07
    ndice
    0.07
     ever
    0.07
    oken
    0.07
    ä½ľçļĦ
    0.07
    缺çĤ¹æĺ¯
    0.07
    è±Ĩçĵ£è¯ĦåĪĨ
    0.07
    tou
    0.07
    ignite
    0.07
    Activations Density 0.000%

    No Known Activations