© 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. 26021
    Prev
    Next
    INDEX
    Explanations

    intensifier "even more"

    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
    æŃ£
    -0.07
    UNA
    -0.07
     very
    -0.07
    æģĴå¿ĥ
    -0.07
    æĺİæĺ¾æıIJé«ĺ
    -0.07
    åѦåı²
    -0.06
    æŃ£æĺ¯
    -0.06
    ç¿ħ
    -0.06
    æ¦Ĥ
    -0.06
    _const
    -0.06
    POSITIVE LOGITS
    ä¸ĬåĬł
    0.11
    ä¸Ĭæ·»
    0.09
    ièrement
    0.08
     nữa
    0.08
    åĬłåī§
    0.08
     dodatkowo
    0.08
     accent
    0.08
    è¦ģ注æĦıçļĦæĺ¯
    0.07
    æĴĩ
    0.07
    强è°ĥäºĨ
    0.07
    Activations Density 0.133%

    No Known Activations