© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 7164
    Prev
    Next
    INDEX
    Explanations

    circulator, document verification, quadrupole, vector, Ribbon, episode, Worker

    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
    Negative Logits
    onta
    -0.07
    uiten
    -0.07
    è¿Ļå°±
    -0.07
    æī¿æĭħä¸ĢåĪĩ
    -0.06
    zep
    -0.06
    FindBy
    -0.06
    èĩªæľī
    -0.06
    orma
    -0.06
    å¤įåĪ¶æĪĸ
    -0.06
    详è§ģ
    -0.06
    POSITIVE LOGITS
    \"
    0.13
    ä¸ĭåĪĹ说æ³ķ
    0.12
     _____
    0.12
     ____
    0.12
     \"
    0.12
    _____
    0.11
    ä¸ĭåĪĹ
    0.11
    ____
    0.11
     ______
    0.11
     _______,
    0.10
    Activations Density 0.026%

    No Known Activations