© 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. 49517
    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
    deren
    -0.08
    >Error
    -0.07
    ach
    -0.07
    amai
    -0.07
    æĬ¬
    -0.07
    é£İæĻ¯åIJįèĥľåĮº
    -0.07
    filer
    -0.07
    æī¶
    -0.07
    èĻ¹
    -0.07
    cia
    -0.06
    POSITIVE LOGITS
    ä¸İåIJĦ
    0.09
    å°Ķé¡¿
    0.08
    æĸ°åĬłåĿ¡
    0.07
    为己
    0.07
    arus
    0.07
    èĭ¥å¹²éĹ®é¢ĺçļĦ解éĩĬ
    0.07
    ÑģÑĤана
    0.07
    .Utils
    0.06
    issing
    0.06
    ä¼ļæĬĬ
    0.06
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.