© 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. 56625
    Prev
    Next
    INDEX
    Explanations

    you want to know

    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
    leftright
    -0.09
    ä¸Ĭä¸Ģç«ł
    -0.09
    æĪij们å°Ĩåľ¨
    -0.08
    èĭ¦ç»ĥ
    -0.08
    ç¥ŀåħµ
    -0.08
    æŶéľĢ
    -0.08
    éļ¾çĤ¹éĹ®é¢ĺ
    -0.08
    è°ĥæŁ¥åıijçİ°
    -0.08
    æĹłæŶæĹłåĪ»
    -0.08
    _CRE
    -0.08
    POSITIVE LOGITS
    楼主
    0.08
     quite
    0.08
    å¯¹ä½łçļĦ
    0.07
    æł¹æį®ä½łçļĦ
    0.07
    I
    0.07
     IMO
    0.07
    åĴĮä½ł
    0.07
     probably
    0.07
    2
    0.07
    å¸®ä½ł
    0.07
    Activations Density 0.964%

    No Known Activations