© 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. 51784
    Prev
    Next
    INDEX
    Explanations

    is, are, can, existence, states

    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
    女éĥİ
    -0.08
    åı¯åĸľ
    -0.08
    нÑĤ
    -0.08
    udou
    -0.08
    ables
    -0.08
     hany
    -0.08
    åĴ«
    -0.08
    ETTO
    -0.08
    ä¸īéĿ¢
    -0.08
    luan
    -0.08
    POSITIVE LOGITS
    ÓĻÑĢ
    0.06
     stuff
    0.06
    çݯèĬĤä¸Ń
    0.06
    ystal
    0.06
     notion
    0.06
    bacher
    0.06
    eraus
    0.06
    è´¸
    0.06
     sens
    0.06
    失æķĪ
    0.06
    Activations Density 0.001%

    No Known Activations