© 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. 41304
    Prev
    Next
    INDEX
    Explanations

    opposite and contrasting concepts

    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
    ascade
    -0.09
    ç¼ĺæķħ
    -0.08
     Additional
    -0.08
     additional
    -0.07
    cule
    -0.07
    into
    -0.07
    è¡·å¿ĥçļĦ
    -0.07
    æĪijçľĭ
    -0.07
    awl
    -0.07
    additional
    -0.07
    POSITIVE LOGITS
    缸åıįçļĦ
    0.13
    缸åıį
    0.13
     contrasting
    0.12
     opposite
    0.12
     contrast
    0.11
     пÑĢоÑĤивополо
    0.11
     contraire
    0.10
     contrasts
    0.10
     oppos
    0.10
     Contrast
    0.10
    Activations Density 0.065%

    No Known Activations