© 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. 3161
    Prev
    Next
    INDEX
    Explanations

    alongside

    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
     Creatures
    -0.08
    èĩ¼
    -0.08
     Portions
    -0.07
     داÙħ
    -0.07
    å¤ļçĤ¹
    -0.07
     pistes
    -0.07
    æīĢ欲è¨Ģ
    -0.07
     Points
    -0.07
    æĪijè¦ģæĬķè¯ī
    -0.07
    onders
    -0.07
    POSITIVE LOGITS
    ç´§éĤ»
    0.14
    缸éĤ»
    0.14
    æİĴåĪĹ
    0.14
     adjacent
    0.13
     juxtap
    0.12
     interle
    0.12
    并åĪĹ
    0.12
     alongside
    0.12
    顺åºı
    0.11
    æİĴåºı
    0.11
    Activations Density 0.489%

    No Known Activations