© 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. 17405
    Prev
    Next
    INDEX
    Explanations

    .org/js

    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
    shiv
    -0.09
    naz
    -0.08
     Zir
    -0.08
    anf
    -0.08
    undet
    -0.08
    гей
    -0.08
    -DD
    -0.08
    astia
    -0.08
    enaire
    -0.08
    WEBPACK
    -0.08
    POSITIVE LOGITS
    0.08
    er
    0.07
    e
    0.06
    yy
    0.06
    éģĩä¸Ĭ
    0.06
     gent
    0.06
     assoc
    0.06
     duplicate
    0.06
     exc
    0.06
     Qu
    0.06
    Activations Density 0.005%

    No Known Activations