© 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. 450
    Prev
    Next
    INDEX
    Explanations

    patent

    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
    ᾶ
    -0.20
    ContentPane
    -0.20
    .getDouble
    -0.19
    WithTag
    -0.19
     (++
    -0.19
    iomanip
    -0.19
    .getFloat
    -0.19
    çļĦæ¨¡æł·
    -0.18
    extras
    -0.18
     wing
    -0.18
    POSITIVE LOGITS
    ä¸ĵåĪ©
    0.38
     patent
    0.34
     Patent
    0.30
     patents
    0.29
    åıijæĺİä¸ĵåĪ©
    0.26
    çĶ³è¯·äºº
    0.26
    âĺ°
    0.26
    çĶ³è¯·
    0.26
    çī¹æ´¾åijĺ
    0.26
     rencont
    0.25
    Activations Density 1.343%

    No Known Activations