© 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. 11602
    Prev
    Next
    INDEX
    Explanations

    protein, factor, homolog, gene, antigen

    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
    å¾Ĺå½ĵ
    -0.08
    urd
    -0.07
    wend
    -0.07
    Stmt
    -0.07
    ä¸įå®Į
    -0.07
    çļĦ主è§Ĥ
    -0.07
    ä»Ģä¹ĪéĹ®é¢ĺ
    -0.07
    zol
    -0.07
    cheme
    -0.07
    igne
    -0.07
    POSITIVE LOGITS
    æĭŁ
    0.09
     linker
    0.08
    åij½åIJį为
    0.08
     accessory
    0.08
     ubiquitous
    0.08
     specificity
    0.08
     genes
    0.08
     gene
    0.08
    æĵ¬
    0.08
     versatile
    0.07
    Activations Density 0.761%

    No Known Activations