© 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. 50743
    Prev
    Next
    INDEX
    Explanations

    combination

    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
    ngh
    -0.07
     pass
    -0.07
    å¸ĿçļĦ
    -0.07
    zez
    -0.07
    é²²
    -0.07
    æľµæľµ
    -0.07
    ÙĩÙĨ
    -0.07
    .outputs
    -0.07
    ekl
    -0.07
    adio
    -0.06
    POSITIVE LOGITS
     combination
    0.10
     комбина
    0.08
     kombin
    0.08
     Kombin
    0.08
     kombinasi
    0.08
    综åIJĪä½ĵ
    0.08
     Combination
    0.08
     combinazione
    0.08
    ç»ĵåIJĪäºĨ
    0.08
     combinação
    0.08
    Activations Density 0.936%

    No Known Activations