© 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. 55195
    Prev
    Next
    INDEX
    Explanations

    bounded solutions

    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
    iming
    -0.08
    åĵ¨
    -0.07
    opter
    -0.07
    åĭĩæ°ĶåĴĮ
    -0.07
    opt
    -0.07
    match
    -0.07
    空çļĦ
    -0.07
    ä¸ĢåŃĹ
    -0.06
    æŬ
    -0.06
    å®īæİĴ
    -0.06
    POSITIVE LOGITS
     bound
    0.10
     bounded
    0.09
     bounds
    0.08
    bounded
    0.08
    _bound
    0.08
     bounding
    0.08
     Bound
    0.08
    Bound
    0.08
    bounding
    0.08
    bound
    0.08
    Activations Density 0.010%

    No Known Activations