© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 11885
    Prev
    Next
    INDEX
    Explanations

    craftsmen, slim lights, medium measuring, tile roofs

    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
    dbo
    -0.08
    ä¸įä¹±
    -0.08
    اÛĮÛĮ
    -0.08
    opup
    -0.08
    ç§ijåijĺ
    -0.07
    ä½łæĺ¯è°ģ
    -0.07
    Å¡in
    -0.07
    ிரà¯ģ
    -0.07
    å®Ŀå®ī
    -0.07
    ereal
    -0.07
    POSITIVE LOGITS
    åīįèĢħ
    0.13
    åIJİèĢħ
    0.10
    尤为
    0.09
    å°¤åħ¶
    0.09
    å±ħå¤ļ
    0.09
     latter
    0.09
    å°¤
    0.08
    尤为éĩįè¦ģ
    0.08
     particularly
    0.08
     Particularly
    0.07
    Activations Density 0.378%

    No Known Activations