© 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. 9468
    Prev
    Next
    INDEX
    Explanations

    geographical locations and specific entities

    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
    çİĩè¾¾
    -0.07
    éĿ¢ç§¯è¾¾
    -0.07
    .pan
    -0.06
    主è¦ģåĪĨ为
    -0.06
    bli
    -0.06
    ä¸ļæľīéĻIJåħ¬åı¸
    -0.06
    æĺ¯ä¸Ģ个éĿŀ常
    -0.06
     divided
    -0.06
    abria
    -0.06
    atis
    -0.06
    POSITIVE LOGITS
     respectively
    0.11
     ê°ģê°ģ
    0.11
    ãģĿãĤĮãģŀãĤĮ
    0.11
    ãģ¨ãģĦãģ£ãģŁ
    0.11
    çŃīåħ¶ä»ĸ
    0.11
    ä¹Łéĥ½
    0.11
     Äijá»ģu
    0.10
    åIJĦæľī
    0.10
    åĪĨåĪ«ä¸İ
    0.10
    ãģ¨ãĤĤãģ«
    0.10
    Activations Density 0.262%

    No Known Activations