© 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. 40804
    Prev
    Next
    INDEX
    Explanations

    other

    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
    ç½®ä¹ĭ
    -0.08
    inggu
    -0.06
    èĩ¨æĻĤ
    -0.06
    å¦Ĥ梦
    -0.06
    cule
    -0.06
    ixon
    -0.06
    izoph
    -0.06
    æģ
    -0.06
    èĢģæľīæīĢ
    -0.06
    cht
    -0.06
    POSITIVE LOGITS
    others
    0.09
     others
    0.08
     importantly
    0.08
    à¸Ńืà¹Īà¸Ļà¹Ĩ
    0.08
     lainnya
    0.08
    other
    0.08
     other
    0.07
    ãģĤãģ¨ãģ¯
    0.07
    åħ¶å®ĥ
    0.07
    uela
    0.07
    Activations Density 0.490%

    No Known Activations