© 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. 60417
    Prev
    Next
    INDEX
    Explanations

    formalisms, presentation, domain

    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
    uez
    -0.08
    åĶ®åīį
    -0.07
     Juz
    -0.07
    .rules
    -0.07
    åı¯æľĽ
    -0.07
     incol
    -0.07
    ä¸įäºĨäºĨ
    -0.07
     truff
    -0.07
    Õ¡Õ½
    -0.07
    ÙĪاÙĤع
    -0.07
    POSITIVE LOGITS
     alternative
    0.12
     equival
    0.12
     equivalent
    0.12
     alternatively
    0.12
     Equivalent
    0.11
    alternative
    0.11
    两ç§įæĸ¹å¼ı
    0.11
     approach
    0.10
     Alternative
    0.10
     alternatif
    0.10
    Activations Density 0.114%

    No Known Activations