© 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. 11380
    Prev
    Next
    INDEX
    Explanations

    other societal problems

    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
    è¶Ĭ
    -0.08
    çŁ¥ä¹ĭ
    -0.07
    ازÛĮ
    -0.07
    omens
    -0.07
    idem
    -0.07
    æł
    -0.07
     mÃŃn
    -0.07
    æĭ¬
    -0.07
    amanan
    -0.07
    дем
    -0.07
    POSITIVE LOGITS
    çŃīåħ¶ä»ĸ
    0.16
     other
    0.13
    çļĦåħ¶ä»ĸ
    0.12
    åħ¶å®ĥ
    0.11
    åħ¶ä»ĸ
    0.11
    æīįæĺ¯
    0.11
    åħ¶ä»ĸæĸ¹å¼ı
    0.10
     elsewhere
    0.10
    other
    0.10
     اÙĦأخرÙī
    0.10
    Activations Density 0.160%

    No Known Activations