© 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. 64618
    Prev
    Next
    INDEX
    Explanations

    repulsion, expulsion

    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
    è¸ıè¸ıå®ŀå®ŀ
    -0.08
     designate
    -0.07
     Alfon
    -0.07
    verty
    -0.07
    iette
    -0.07
    復帰
    -0.07
    缴æİ¥æĪĸ
    -0.07
     Alloc
    -0.07
    ken
    -0.06
     complet
    -0.06
    POSITIVE LOGITS
    irsch
    0.08
    åĪĨç«ĭ
    0.07
    æİĴæĸ¥
    0.07
    çģ¼
    0.07
    å½¼æѤ
    0.07
    åĻ¬
    0.07
    _partitions
    0.07
     unchecked
    0.07
     increasing
    0.07
     weakening
    0.07
    Activations Density 0.001%

    No Known Activations