© 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. 41609
    Prev
    Next
    INDEX
    Explanations

    increase, decrease, number

    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
    åĪ»
    -0.06
    主æŨ
    -0.06
    å·²éĢļè¿ĩ
    -0.06
    ç«ŀ
    -0.05
    è¿IJåĬ¿
    -0.05
    çľĭä»ĸ
    -0.05
    è¿ĺæľīä¸ĢäºĽ
    -0.05
    Âł
    -0.05
    让åħ¶
    -0.05
    eme
    -0.05
    POSITIVE LOGITS
    linna
    0.09
    éĢĻéłħ
    0.08
    æĽ¿å°¼
    0.08
    ãģijãģ°
    0.08
    çļĦè¿Ļ个
    0.08
    è¿ĻèĤ¡
    0.08
    ç½ĹæĽ¼
    0.08
    å¤įæ£Ģ
    0.08
    ELIT
    0.08
     nasta
    0.08
    Activations Density 0.011%

    No Known Activations