© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 62671
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions or symbols

    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
     Collider
    -0.10
    кÑĥл
    -0.09
     frustra
    -0.09
    erland
    -0.09
     escalate
    -0.09
     undermin
    -0.09
    èµĦæĸĻä¸ĭè½½
    -0.09
    #for
    -0.08
    .hom
    -0.08
    ç²Ľ
    -0.08
    POSITIVE LOGITS
     v
    0.07
    ,
    0.07
     §
    0.06
     &
    0.06
     ming
    0.06
     ft
    0.06
    âĸł
    0.06
     (§
    0.06
    ä¸įä¸ĭ
    0.06
    ä¸įè¡Į
    0.06
    Activations Density 0.182%

    No Known Activations