© 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. 13797
    Prev
    Next
    INDEX
    Explanations

    consequence or result

    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
     nevertheless
    -0.09
    lane
    -0.08
    LAN
    -0.08
    åħ±è®¡
    -0.08
     nonetheless
    -0.08
     infatti
    -0.07
    并举
    -0.07
    Ŀ¼
    -0.07
     Mile
    -0.07
    ][:
    -0.07
    POSITIVE LOGITS
     indirectly
    0.10
    ä¹Łå°±
    0.10
    è¿ĽèĢĮ
    0.10
     consequently
    0.09
    éĹ´æİ¥
    0.09
     consequ
    0.09
     conséqu
    0.09
    éļıä¹ĭ
    0.09
    ä¹Łéļıä¹ĭ
    0.09
    å½±åĵįåĪ°
    0.08
    Activations Density 0.131%

    No Known Activations