© 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. 26971
    Prev
    Next
    INDEX
    Explanations

    extends / le

    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
    decltype
    -0.09
    /Foundation
    -0.08
    emoc
    -0.08
    åīįèĮħ
    -0.08
    aira
    -0.08
    ÙĬسÙĬ
    -0.08
    é¾Ļ
    -0.08
    elmet
    -0.08
    æł¹æį®åľ°
    -0.08
    ENCIL
    -0.08
    POSITIVE LOGITS
    eka
    0.06
    0.06
    çĽij
    0.05
     dep
    0.05
     ph
    0.05
     natural
    0.05
    eee
    0.05
    ä¸Ķä¸į
    0.05
     -
    0.05
    æīĢæĭ¥æľīçļĦ
    0.05
    Activations Density 0.065%

    No Known Activations