© 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. 40651
    Prev
    Next
    INDEX
    Explanations

    border solid px

    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
    åĪĨå¸ĥ
    -0.07
    enburg
    -0.07
     distribution
    -0.07
    æģ¯çļĦ
    -0.06
    empo
    -0.06
    orama
    -0.06
    velt
    -0.06
    å°ĺ
    -0.06
    veld
    -0.06
     Restricted
    -0.06
    POSITIVE LOGITS
    è¾¹æ¡Ĩ
    0.11
     borders
    0.11
     border
    0.10
     Borders
    0.10
    ç¸ģ
    0.09
    -border
    0.09
     borderColor
    0.09
     perimeter
    0.09
    éĤĬ
    0.09
    Border
    0.09
    Activations Density 0.038%

    No Known Activations