© 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. 10446
    Prev
    Next
    INDEX
    Explanations

    cube or square shape

    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
    山大
    -0.07
    åľ¨çľī
    -0.07
    æŃ£å®Ĺ
    -0.07
    åĴĮä½ľçĶ¨
    -0.07
    漪
    -0.07
    andering
    -0.07
     اÙĦاØŃ
    -0.07
    åij»
    -0.07
     Ñĩего
    -0.07
    fork
    -0.06
    POSITIVE LOGITS
    _bbox
    0.09
    åĨħç»ı
    0.08
     RECT
    0.08
    (square
    0.07
    olumn
    0.07
     interior
    0.07
    ClientRect
    0.07
    cience
    0.07
    ovich
    0.07
    åĨħ设
    0.07
    Activations Density 0.007%

    No Known Activations