© 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. 43096
    Prev
    Next
    INDEX
    Explanations

    acronym expansions

    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
    หม
    -0.07
    ivan
    -0.07
     pek
    -0.06
    ä½ıçļĦ
    -0.06
    ä½ı
    -0.06
    Carthy
    -0.06
    ujur
    -0.06
    å¿ĹæĪIJ
    -0.06
    ä¸ĬèµĽåŃ£
    -0.06
    avantage
    -0.06
    POSITIVE LOGITS
     appunto
    0.08
    缸åħ³æݨèįIJ
    0.08
    -controls
    0.07
    ìĹŃ
    0.07
    croll
    0.07
     weiterlesen
    0.06
    çĽ¸ä¼¼æĸĩçĮ®
    0.06
    inste
    0.06
    ael
    0.06
    bucks
    0.06
    Activations Density 0.122%

    No Known Activations