© 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. 63756
    Prev
    Next
    INDEX
    Explanations

    combination of elements

    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
     LIM
    -0.07
    æµ·éĩı
    -0.07
    Lim
    -0.07
    ä¸īéĥ¨
    -0.07
    å®ŀåIJį
    -0.07
    abet
    -0.06
    UCE
    -0.06
    ä¸ĩäºĭ
    -0.06
     Las
    -0.06
    åįĥ家ä¸ĩæĪ·
    -0.06
    POSITIVE LOGITS
     combination
    0.09
     combinations
    0.08
     perpendicular
    0.08
     Combination
    0.07
    combination
    0.07
     combinação
    0.07
    ohn
    0.07
    ç»ĦåIJĪ
    0.07
    plementary
    0.07
     combining
    0.07
    Activations Density 0.001%

    No Known Activations