© 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. 10733
    Prev
    Next
    INDEX
    Explanations

    tokens following certain words

    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
    é¹
    -0.08
     Ø¥Ùħا
    -0.08
    ##_
    -0.08
    either
    -0.08
    è¦ģä¹Ī
    -0.08
    æŁ¥çľĭåħ¨éĥ¨
    -0.08
    缸åħ³éĹ®çŃĶ
    -0.08
    èİħ
    -0.08
    éļĪ
    -0.08
    autoload
    -0.08
    POSITIVE LOGITS
     additionally
    0.12
    尤为
    0.10
     additional
    0.10
    å°¤
    0.09
    å°¤åħ¶
    0.09
    additional
    0.09
     particularly
    0.09
    ä¹Łä¸įä¾ĭå¤ĸ
    0.08
     specifically
    0.08
    ä¸įåIJĮçļĦæĺ¯
    0.08
    Activations Density 0.302%

    No Known Activations