© 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. 26229
    Prev
    Next
    INDEX
    Explanations

    negative numbers or ratings

    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
    çľŁå¥½
    -0.07
    usalem
    -0.07
    丸
    -0.07
    Ý
    -0.07
    æ»´
    -0.07
    ä¸įç¡®å®ļ
    -0.07
    æ£
    -0.07
    å¾ĹçĽĬäºİ
    -0.06
     dope
    -0.06
    æ»´æ°´
    -0.06
    POSITIVE LOGITS
    æĤ²åĵĢ
    0.09
    egative
    0.09
     backwards
    0.09
     negativ
    0.09
     :(
    0.09
    æĤ²æĥ¨
    0.08
     negatively
    0.08
    ]=-
    0.08
    æģ¶æĢ§
    0.08
    é£İå¯Ĵ
    0.08
    Activations Density 0.048%

    No Known Activations