© 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
    2. Qwen3.5-9B Base
    3. 15-QWENSCOPE-RES-64K
    4. 39786
    Prev
    Next
    INDEX
    Explanations

    code file extension or status

    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
    çĤ¹åľ¨
    -0.11
    å¹´åľ¨
    -0.11
    åľ°åľ¨
    -0.11
    åŃIJåľ¨
    -0.10
    äººåľ¨
    -0.10
    åħ¶åľ¨
    -0.10
    åľ°ä¸ĬçļĦ
    -0.10
    æľĪåľ¨
    -0.10
    æ´»åĬ¨åľ¨
    -0.10
    æĹ¶éĹ´åľ¨
    -0.10
    POSITIVE LOGITS
    çļĦæĶ¯æĮģä¸ĭ
    0.18
    çļĦåŁºç¡Ģä¸Ĭ
    0.17
    )}}
    0.16
    çļĦä½ľç͍ä¸ĭ
    0.16
    åĮ»çĶŁçļĦæĮĩ导ä¸ĭ
    0.16
    åĮ»çĶŁæĮĩ导ä¸ĭ
    0.16
    çļĦä¸ĸçķĮéĩĮ
    0.15
    çļĦ帮åĬ©ä¸ĭ
    0.15
    çļĦåīįæıIJä¸ĭ
    0.15
    çļĦèĥĮæĻ¯ä¸ĭ
    0.15
    Activations Density 0.013%

    No Known Activations