© 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
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 30238
    Prev
    Next
    INDEX
    Explanations

    numbers and units

    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
    ÏĥÏĦι
    -0.08
    неÑĢа
    -0.08
    angga
    -0.08
    AGMA
    -0.08
    lande
    -0.08
    åħ¥éĩij
    -0.07
     Slov
    -0.07
    entino
    -0.07
    éĥ½æľīäºĨ
    -0.07
    roj
    -0.07
    POSITIVE LOGITS
     theoretically
    0.09
    ãģ¥
    0.08
     or
    0.08
    æĪĸ以ä¸Ĭ
    0.07
    ãģļãģ¤
    0.07
    oret
    0.07
    æĪĸ
    0.07
    åĽĽæĸ¹
    0.07
    Opp
    0.06
     ëĺIJëĬĶ
    0.06
    Activations Density 0.195%

    No Known Activations