© 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. 38768
    Prev
    Next
    INDEX
    Explanations

    actions or events being communicated

    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
    ilik
    -0.08
    ÅĤÄĻ
    -0.07
    nost
    -0.07
    apun
    -0.07
    åħ´åĽ½
    -0.07
    istogram
    -0.07
    elijk
    -0.06
    ä¸Ģä¸Ŀä¸įèĭŁ
    -0.06
    ниÑĨÑĮ
    -0.06
     regarded
    -0.06
    POSITIVE LOGITS
     siÄĻ
    0.12
    irse
    0.11
     themselves
    0.10
     itself
    0.10
    ÑģÑı
    0.10
     zichzelf
    0.10
     diri
    0.10
    éĺħ读åħ¨æĸĩ
    0.09
    ÑĤÑģÑı
    0.09
    edException
    0.09
    Activations Density 0.367%

    No Known Activations