© 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
    2. Qwen3.5-9B Base
    3. 15-QWENSCOPE-RES-64K
    4. 43728
    Prev
    Next
    INDEX
    Explanations

    even if

    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
     zwar
    -0.08
     إذÙĨ
    -0.08
     inoltre
    -0.08
    è¦ģä¹Ī
    -0.08
    ä¹ĭæīĢ以
    -0.08
     ugyanis
    -0.08
    à¹Īา
    -0.08
    æĢİä¹ĪåĬŀåij¢
    -0.07
     tehát
    -0.07
    onos
    -0.07
    POSITIVE LOGITS
    à¸ģà¹ĩà¸ķาม
    0.09
     it
    0.09
    å®ĥ
    0.08
    å®ĥæĺ¯
    0.08
    å®ĥ们æĺ¯
    0.08
     dalamnya
    0.08
    ãģĿãĤĮãģ¯
    0.08
    æľīäºĽä¸į
    0.08
    å®ĥ以
    0.07
    å®ĥä¹Ł
    0.07
    Activations Density 0.158%

    No Known Activations