© 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. 49229
    Prev
    Next
    INDEX
    Explanations

    constraints and limits

    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
    á»ijn
    -0.07
     cont
    -0.07
    ych
    -0.07
    ä¸įæį¢
    -0.07
     weather
    -0.07
    ä¸İä¼Ĺä¸įåIJĮ
    -0.07
     intoxic
    -0.06
    ä¸įæĶ¹
    -0.06
    åĮºåĪ«äºİ
    -0.06
    enstr
    -0.06
    POSITIVE LOGITS
    æľªåıijçİ°
    0.09
    imits
    0.09
     stringent
    0.09
    ä¸ĭéĻIJ
    0.09
    limits
    0.09
    æİ¢æµĭ
    0.09
    缮åīį没æľī
    0.09
     Limits
    0.08
     limits
    0.08
    bard
    0.08
    Activations Density 0.016%

    No Known Activations