© 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. 10609
    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
    æIJľå¯»
    -0.07
    mert
    -0.07
    wing
    -0.06
    ÑĢиÑĦ
    -0.06
    ä¸ĩåĪĨ
    -0.06
    ÑĢай
    -0.06
    çĻ¾åĪĨ
    -0.06
    arend
    -0.06
    Fix
    -0.06
    hook
    -0.06
    POSITIVE LOGITS
    æĬµæ¶Ī
    0.09
     inconvenient
    0.08
    æĴ¤
    0.08
    ä¸Ĭæ¡Į
    0.08
    平衡
    0.08
    æĢİä¹ĪåĬŀåij¢
    0.08
    ·¸
    0.08
    ç«
    0.08
    å¤ļæĥ³
    0.08
    pray
    0.07
    Activations Density 0.000%

    No Known Activations