© 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. 18407
    Prev
    Next
    INDEX
    Explanations

    nature, universe, cosmic, natural

    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
    jep
    -0.08
    -needed
    -0.08
    adata
    -0.08
    èħĨ
    -0.08
    èįĨæ£ĺ
    -0.08
    æŁ¥æ¼ı
    -0.08
    понен
    -0.08
     legale
    -0.08
    bersome
    -0.08
    çĮ¬
    -0.08
    POSITIVE LOGITS
    èĩªçĦ¶çķĮ
    0.13
     natural
    0.11
    èĩªçĦ¶
    0.11
    ä¸ĩçī©
    0.11
     Nature
    0.10
    è§Ħå¾ĭ
    0.10
    çļĦèĩªçĦ¶
    0.10
     Natural
    0.10
    natural
    0.10
    çĶŁçī©çļĦ
    0.09
    Activations Density 0.033%

    No Known Activations