© 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. 17554
    Prev
    Next
    INDEX
    Explanations

    articles before nouns

    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
    acce
    -0.08
    ä¸ĸä¿Ĺ
    -0.07
    å½ĵåľ°äºº
    -0.07
    pector
    -0.07
    aura
    -0.07
    akar
    -0.07
    RelativeTo
    -0.07
    .Restr
    -0.07
    ogg
    -0.07
    ç«ĭæ³ķéĻ¢
    -0.07
    POSITIVE LOGITS
    å°¤åħ¶æĺ¯
    0.08
    çIJĨè®ºçŁ¥è¯Ĩ
    0.08
    çī¹ãģ«
    0.08
     Especially
    0.08
     especially
    0.07
    æŃ£å¸¸ä½¿çĶ¨
    0.07
     Particularly
    0.07
     particularly
    0.07
    æŃ£å¸¸
    0.07
    çī¹åĪ«æĺ¯
    0.07
    Activations Density 1.013%

    No Known Activations