© 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. 8169
    Prev
    Next
    INDEX
    Explanations

    Here starts context

    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
     this
    -0.10
    éĤ£ä¹Īåľ¨
    -0.10
     therein
    -0.09
     thereafter
    -0.09
    åľ¨æѤ
    -0.09
    æį®æѤ
    -0.08
    è¿ĻæŶ
    -0.08
    åħ¶åľ¨
    -0.08
    çĶ±æѤ
    -0.08
    è¿Ļæĺ¯ä¸ª
    -0.08
    POSITIVE LOGITS
    å·²ç»ıå°Ĩ
    0.10
    å·²ç»ıä¸įæĺ¯
    0.09
    éĩĩçĶ¨çļĦæĺ¯
    0.09
    oldt
    0.09
    èĻ½çĦ¶æ²¡æľī
    0.09
    çĶ¨çļĦæĺ¯
    0.09
    åĩºäºĨä¸Ģ个
    0.08
     Ñıвно
    0.08
    ablish
    0.08
    ãģĺãĤģãģ¦
    0.08
    Activations Density 0.143%

    No Known Activations