© 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. 18291
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions or programming code

    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
     whereas
    -0.07
    åѦä¸İ
    -0.06
    èĢĮè¿Ļ
    -0.06
     {}.
    -0.06
     "".
    -0.06
    çī¹çĤ¹åĴĮ
    -0.06
    um
    -0.06
    (++
    -0.06
    umo
    -0.06
     },
    -0.06
    POSITIVE LOGITS
    çļĦè¯Ħä»·æĺ¯
    0.11
    ")==
    0.11
    ãģĻãĤĭãģĵãģ¨ãģ¯
    0.11
    ])==
    0.10
    ãģĹãģŁãģ®ãģ¯
    0.10
    åģļçļĦå°±æĺ¯
    0.10
    çļĦ人æĿ¥è¯´
    0.09
    ãģĻãĤĭãģ®ãģ¯
    0.09
    çŃīéĥ½æĺ¯
    0.09
    ãģĭãģ¯
    0.09
    Activations Density 0.013%

    No Known Activations