© 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. Qwen2.5-7B-IT
    5. 20-MATRYOSHKA-65K
    7. 315
    Prev
    Next
    INDEX
    Explanations

    code/template elements

    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
    @student
    -0.30
     Prostit
    -0.28
    æĪĺ士èģĮä¸ļ
    -0.27
    ä¸ī大èģĮä¸ļ
    -0.26
    -eslint
    -0.26
     our
    -0.25
    æĪij们çļĦ
    -0.25
    游æĪıåī¯æľ¬
    -0.25
    æľīçļĦçݩ家
    -0.25
     ’
    -0.25
    POSITIVE LOGITS
    [c
    0.39
    Template
    0.38
     "
    0.34
     Template
    0.32
     ,[
    0.32
    [
    0.32
    ,[
    0.31
    []
    0.30
    âģĦ
    0.29
     ""
    0.28
    Activations Density 8.289%

    No Known Activations