© 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. 15000
    Prev
    Next
    INDEX
    Explanations

    mean, deviation, statistics

    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
    odel
    -0.07
    posa
    -0.07
    WB
    -0.07
     mie
    -0.07
    .inject
    -0.07
    åĨ³å®ļæĺ¯åIJ¦
    -0.07
    à¥įलà¥Ģ
    -0.07
    èī°éļ¾
    -0.07
    æĥĬéŃĤ
    -0.07
    çĿIJ
    -0.07
    POSITIVE LOGITS
     demean
    0.09
    -mean
    0.09
     deviations
    0.08
    ÑĨенÑĤÑĢи
    0.08
    çļĦå¹³åĿĩ
    0.08
     deviation
    0.08
    å¹³åĿĩ
    0.08
    çŁ³æ¦´
    0.08
    íľĺ
    0.08
    æĸ¹å·®
    0.08
    Activations Density 0.004%

    No Known Activations