© 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. 19883
    Prev
    Next
    INDEX
    Explanations

    metric element

    np_acts-logits-general · gemini-2.5-flash-lite
    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
    æ¯ı次
    -0.08
    éĩĬ
    -0.07
     upset
    -0.07
    æ¸łéģĵ
    -0.07
    ä¸Ĭ次
    -0.07
    æī£
    -0.07
    ä¸ĭ次
    -0.07
    次
    -0.07
    éĴ£
    -0.06
    ebp
    -0.06
    POSITIVE LOGITS
    opan
    0.09
     Tiss
    0.08
     scl
    0.07
     extrad
    0.07
    ç»ĩ
    0.07
     ÑĥÑİÑĤ
    0.07
    दि
    0.07
     Killing
    0.07
    è¾
    0.07
     smoothly
    0.07
    Activations Density 0.004%

    No Known Activations