© 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. 15689
    Prev
    Next
    INDEX
    Explanations

    country, state, or entity names

    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
    à¸Ļำà¹Ħà¸Ľ
    -0.07
    彬
    -0.07
    schw
    -0.06
    æĻĸ
    -0.06
    ãģĮãģĦ
    -0.06
    çļĦä½ľçĶ¨ä¸ĭ
    -0.06
    çĩ¥
    -0.06
    åľ¨éĩĮéĿ¢
    -0.06
    à¹Ģà¸Ľà¹ĩà¸Ļà¸ķัว
    -0.06
    该åħ¬åı¸
    -0.06
    POSITIVE LOGITS
    åįģåĪĨéĩįè§Ĩ
    0.09
    ä¹ĭæīĢ以
    0.09
    ãģ«éĻIJ
    0.09
    ãģ«ãģĬãģijãĤĭ
    0.09
    æľ¨æľī
    0.08
    éĩĩçĶ¨çļĦæĺ¯
    0.08
    ::$
    0.08
    ::$_
    0.08
    ãģ«ãĤĪãģ£ãģ¦ãģ¯
    0.08
    çļĦ大éĥ¨åĪĨ
    0.08
    Activations Density 0.100%

    No Known Activations