© 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. 19628
    Prev
    Next
    INDEX
    Explanations

    boundary and transition points

    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
    enske
    -0.07
    سÙĪب
    -0.07
     memadai
    -0.07
    bán
    -0.07
    åħĨ
    -0.07
    åIJĦæĸ¹éĿ¢
    -0.07
     bén
    -0.07
    esn
    -0.07
    سازÛĮ
    -0.07
    ä¸į足çļĦ
    -0.07
    POSITIVE LOGITS
     boundaries
    0.09
     transitions
    0.09
    è¾¹çķĮ
    0.08
     transitioning
    0.08
     boundary
    0.08
    ãģ¨ãģĵãĤįãģ§ãģĻ
    0.08
    Transition
    0.07
     endpoints
    0.07
    _transition
    0.07
     пеÑĢеÑħода
    0.07
    Activations Density 0.006%

    No Known Activations