© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen2.5-7B-IT
    5. 20-MATRYOSHKA-65K
    7. 1245
    Prev
    Next
    INDEX
    Explanations

    wanting or desiring

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    chanind/qwen2.5-7B-it-layer-20-saes/pile/matryoshka/k-100
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    .VideoCapture
    -0.27
     typingsJapgolly
    -0.22
     simply
    -0.22
     AssemblyVersion
    -0.22
    轫
    -0.21
     typingsSlinky
    -0.21
    ðŁĻĤ
    -0.20
    âce
    -0.20
    usaha
    -0.20
     __("
    -0.19
    POSITIVE LOGITS
     desired
    0.37
    欲
    0.31
    ä½łæĥ³
    0.30
    ä½łè¦ģ
    0.29
     wished
    0.27
    è¦ģ
    0.27
    desired
    0.26
     wanted
    0.25
     desire
    0.23
     eg
    0.23
    Activations Density 1.235%

    No Known Activations