© 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. 19866
    Prev
    Next
    INDEX
    Explanations

    Of course,

    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
    è¦ģä¹Ī
    -0.08
     EITHER
    -0.08
    è¦ģä¹Īæĺ¯
    -0.08
     either
    -0.08
    çĶļèĩ³æ¯Ķ
    -0.08
    éĤ£ä¹Īä½ł
    -0.07
    åıĪæĪĸèĢħ
    -0.07
    ãģ©ãģĨãģĭ
    -0.07
     enten
    -0.07
    æīĢ以说
    -0.07
    POSITIVE LOGITS
    åķ¦
    0.10
    ãģªãģĮãĤī
    0.09
    çĦ¶å¤§
    0.09
    erweise
    0.08
    çĦ¶çļĦ
    0.08
    å½ĵçĦ¶
    0.08
    åħįä¸įäºĨ
    0.08
    ãģĹãĤĤ
    0.08
    å½ĵçĦ¶æĺ¯
    0.08
    åĸ½
    0.08
    Activations Density 0.096%

    No Known Activations