© 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. 48134
    Prev
    Next
    INDEX
    Explanations

    difference between

    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
    æ´Ľä¼Ĭ
    -0.08
    à¹Īาà¸Ļ
    -0.08
    ateg
    -0.07
    ÙĨدÙĨ
    -0.07
    ä¸ĵæłıæĶ¶å½ķ该åĨħ容
    -0.07
    ovich
    -0.07
    ä¸ĭåIJĮ
    -0.07
    tesi
    -0.07
    lesa
    -0.06
     cosy
    -0.06
    POSITIVE LOGITS
     ê²ĥìĿ´ê³ł
    0.08
    åıĬ对
    0.08
    ãĢįãĢģ
    0.07
    å¸Ńåį·
    0.07
    以åıĬåľ¨
    0.07
    )&&
    0.07
    )&&(
    0.07
    éĢIJ
    0.06
    以åıĬå¦Ĥä½ķ
    0.06
    itat
    0.06
    Activations Density 0.039%

    No Known Activations