© 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. 21425
    Prev
    Next
    INDEX
    Explanations

    SQL `INSERT INTO`

    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
     nbytes
    -0.08
    ä¿¡æģ¯åħ¬å¼Ģ
    -0.08
     ÙĨاØŃ
    -0.07
    asha
    -0.07
    ISA
    -0.07
     elapsed
    -0.07
    MSN
    -0.07
    åĸ«èĮ¶
    -0.07
    ç¯
    -0.06
    inci
    -0.06
    POSITIVE LOGITS
    æķıæĦŁ
    0.08
    åĽ
    0.07
    ãģĿãģ®ä»ĸãģ®
    0.07
    以åıĬåħ¶ä»ĸ
    0.07
     sensitive
    0.07
    ç¨Ģå¥ĩ
    0.07
    ariato
    0.07
    ä¸Ńãģ§ãĤĤ
    0.07
    äksi
    0.07
    åĽłä¸ºè¿ĻäºĽ
    0.07
    Activations Density 0.045%

    No Known Activations