© 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. 32924
    Prev
    Next
    INDEX
    Explanations

    fruit and fruits

    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
    èļĵ
    -0.07
    èľĪ
    -0.07
    webpack
    -0.07
    çĥ¤é±¼
    -0.07
    鲸
    -0.07
    amping
    -0.07
    èļ£
    -0.07
    èļ¯èļĵ
    -0.06
    稻çĶ°
    -0.06
     beige
    -0.06
    POSITIVE LOGITS
    æŀľå®ŀ
    0.11
    æŀľèĤī
    0.11
    fruit
    0.10
    éħ¸çĶľ
    0.10
    ä¸Ģé¢Ĺ
    0.10
    æŀĿ头
    0.10
     fruit
    0.10
    累累
    0.09
    æłijä¸ĬçļĦ
    0.09
    æ±ģ
    0.09
    Activations Density 0.119%

    No Known Activations