© 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. 38836
    Prev
    Next
    INDEX
    Explanations

    to + verb + subsequent word

    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
    åĽłä¸ºå¥¹
    -0.08
    éĢļè¿ĩå¼Ģå±ķ
    -0.08
    angat
    -0.07
    æīĢ以对äºİ
    -0.07
    TTY
    -0.07
    åĽłä¸ºåľ¨
    -0.07
     Tatsache
    -0.07
    åıĹåĪ°äºĨ
    -0.07
    åĽłä¸ºæľī
    -0.07
    ãģįãģ£ãģ¨
    -0.07
    POSITIVE LOGITS
    èµ·è§ģ
    0.16
     properly
    0.08
    ãģĻãĤĭãģ«ãģ¯
    0.08
     ×ķ׾×Ķ
    0.08
     oneself
    0.08
     ÑģобÑģÑĤвенно
    0.08
     ÙģØ¥ÙĨÙĩ
    0.08
    orney
    0.07
    è§Ĵ度çľĭ
    0.07
    æĢİä¹ĪåĬŀåij¢
    0.07
    Activations Density 0.094%

    No Known Activations