© 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. 42385
    Prev
    Next
    INDEX
    Explanations

    prone to

    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
    usch
    -0.09
    ahir
    -0.09
    ainless
    -0.08
    ain
    -0.08
    ildo
    -0.07
    å¿ħè¦ģ
    -0.07
     необÑħодим
    -0.07
    åı¯ä»¥å¸®åĬ©
    -0.07
    ¬
    -0.07
    åĬªåĬĽæıIJé«ĺ
    -0.07
    POSITIVE LOGITS
    ä¹Łå®¹æĺĵ
    0.11
    èĢĮä¸Ķä¹Ł
    0.09
     nowadays
    0.08
    zier
    0.08
    èĢĮä¸Ķè¿ĺæĺ¯
    0.08
     dÃłng
    0.08
     ×ŀ×IJ×ķ×ĵ
    0.08
    Ùij
    0.08
    èĢĮä¸Ķè¿ĺ
    0.08
    èĢĮä¸Ķæĺ¯
    0.08
    Activations Density 0.020%

    No Known Activations