© 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. 45126
    Prev
    Next
    INDEX
    Explanations

    twins"

    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
    olygon
    -0.07
     alc
    -0.07
    soc
    -0.07
    redito
    -0.07
    ê³ł
    -0.06
     sem
    -0.06
    é«ĺçħ§
    -0.06
    atin
    -0.06
    人说
    -0.06
    ÙĪØ®
    -0.06
    POSITIVE LOGITS
    isma
    0.08
    ugged
    0.07
     ugyanis
    0.07
    opedia
    0.07
     "^
    0.07
    aksa
    0.07
    åĢŁ
    0.07
    就没
    0.07
    _inner
    0.07
    elsing
    0.07
    Activations Density 0.755%

    No Known Activations