© 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. 26725
    Prev
    Next
    INDEX
    Explanations

    gene imprinting and parent-of-origin effects

    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
    åĨµ
    -0.09
    åĬ©äºº
    -0.06
    ointment
    -0.06
    ä¸İç»´ä¿®
    -0.06
    flug
    -0.06
    ÑħÑĸ
    -0.06
    oque
    -0.06
     தà¯ĩ
    -0.06
    antos
    -0.06
    æĹłæ°´
    -0.06
    POSITIVE LOGITS
    UBE
    0.07
    å¾ĪæĹ©
    0.07
     resolved
    0.07
    æŃ¤èµ·
    0.07
    æľīä¸ĢåįĬ
    0.07
     mamm
    0.07
    AZY
    0.07
     switching
    0.07
    æ²īçĿ¡
    0.07
     selectively
    0.07
    Activations Density 0.022%

    No Known Activations