© 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. 63186
    Prev
    Next
    INDEX
    Explanations

    lambda(ex)

    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
    ichern
    -0.07
    appe
    -0.07
    æĸ¹ãģ§
    -0.07
    igny
    -0.07
    èªĩ
    -0.07
    æŃ£è§ĦåĮ»éĻ¢
    -0.07
    asury
    -0.07
    .jquery
    -0.07
     Schmer
    -0.07
    adol
    -0.07
    POSITIVE LOGITS
    æ¯Ľ
    0.08
    äº
    0.07
    utnik
    0.06
     Watkins
    0.06
    obr
    0.06
    磨
    0.06
    éĺľ
    0.06
    çļĦåı¦ä¸Ģ
    0.06
    ä¸īåĪĨ
    0.06
    =""><
    0.06
    Activations Density 0.001%

    No Known Activations