© 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. 29188
    Prev
    Next
    INDEX
    Explanations

    that followed by noun/pronoun

    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
    è¾¾æĸ¯
    -0.08
    è¿Ļå°±è¦ģæ±Ĥ
    -0.07
    书åIJ§
    -0.07
    说åIJ§
    -0.07
    æīĢ以说
    -0.07
    ulti
    -0.07
     gelingt
    -0.07
    åıijå¸ĥäºİ
    -0.07
    ="__
    -0.07
    å¤ĸæı´
    -0.07
    POSITIVE LOGITS
     ÑıкобÑĭ
    0.08
     ÙĪØ£ÙĨÙĩ
    0.07
    conditionally
    0.07
     blah
    0.07
    并表示
    0.06
     Winchester
    0.06
     شأÙĨ
    0.06
    æĺİæĹ¥
    0.06
    æĸĹ
    0.06
    并è¦ģæ±Ĥ
    0.06
    Activations Density 0.347%

    No Known Activations