© 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. 45105
    Prev
    Next
    INDEX
    Explanations

    creative, cutting, solar, calculus, multi

    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
    å°¤åħ¶
    -0.08
    å°¤åħ¶åľ¨
    -0.08
     particul
    -0.07
     firstly
    -0.07
    å°¤åħ¶æĺ¯åľ¨
    -0.07
    éĻ¤äºĨ
    -0.07
    itude
    -0.07
    çŃī缸åħ³
    -0.07
    空åīį
    -0.07
    æĥħåĨµåIJİ
    -0.06
    POSITIVE LOGITS
    åĨįåĪ°
    0.14
     sekalipun
    0.12
    æľĢæĸ°çļĦ
    0.09
     ÙĪØŃتÙī
    0.09
     persino
    0.09
    çĶļèĩ³è¿ĺæľī
    0.09
    åĴĮæľĢ
    0.09
     downright
    0.09
     addirittura
    0.09
    çĶļèĩ³è¿ŀ
    0.08
    Activations Density 0.251%

    No Known Activations