© 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. 13453
    Prev
    Next
    INDEX
    Explanations

    colors and neutral tones

    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
     conv
    -0.07
    رع
    -0.07
    ç¥ŀåħµ
    -0.07
     chor
    -0.06
    å¾Ĵ
    -0.06
    ows
    -0.06
     Wong
    -0.06
    ulu
    -0.06
    ingles
    -0.06
    imed
    -0.06
    POSITIVE LOGITS
    çĻ¾æIJŃ
    0.09
     neutral
    0.08
    Neutral
    0.08
    æ»ļå±ı
    0.08
     tones
    0.08
    -neutral
    0.08
    endre
    0.08
    cate
    0.08
    Clr
    0.08
    neos
    0.08
    Activations Density 0.090%

    No Known Activations