© 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. 27217
    Prev
    Next
    INDEX
    Explanations

    mathematical operators or conditions

    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
    æ²īæĢĿ
    -0.06
    iums
    -0.06
    EME
    -0.06
    vro
    -0.06
    aur
    -0.06
     CHUNK
    -0.06
    ahl
    -0.06
    iger
    -0.06
    å¨ģæĸ¯
    -0.06
    kv
    -0.06
    POSITIVE LOGITS
    åĨ³å®ļæĺ¯åIJ¦
    0.11
    èĭ¥è¦ģ
    0.10
    æĿ¥åĪ¤æĸŃ
    0.09
    èĭ¥åľ¨
    0.09
    æĺ¯åIJ¦æŃ£å¸¸
    0.09
     decisive
    0.09
    æĺ¯åIJ¦åľ¨
    0.09
     equality
    0.08
    并确ä¿Ŀ
    0.08
    ä½Ĩåıªè¦ģ
    0.08
    Activations Density 0.097%

    No Known Activations