© 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. 10491
    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
    cae
    -0.07
    ritch
    -0.07
    kdir
    -0.07
    eldorf
    -0.07
    <small
    -0.07
    AccessException
    -0.07
    rts
    -0.07
    angles
    -0.07
    koa
    -0.07
    åįĪåIJİ
    -0.06
    POSITIVE LOGITS
    egov
    0.07
    kaw
    0.07
    поло
    0.06
    æīĢæľīçļĦ
    0.06
     {}).
    0.06
    æĺ¯ä¸Ģ个éĿŀ常
    0.06
    è¿Ľè¡Įè°ĥæŁ¥
    0.06
    绯
    0.06
    庫
    0.06
    Assembly
    0.06
    Activations Density 0.000%

    No Known Activations