© 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. 1330
    Prev
    Next
    INDEX
    Explanations

    Technical terms

    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
     libertin
    -0.36
    ESSAGE
    -0.30
     ×Ķ×ķ×ĵ
    -0.29
    ¡´
    -0.29
     vö
    -0.28
     èĩªåĬ¨çĶŁæĪIJ
    -0.28
     moden
    -0.27
    ).^
    -0.27
     addCriterion
    -0.26
     burge
    -0.26
    POSITIVE LOGITS
     M
    0.22
    ĭ
    0.21
     R
    0.20
     eventName
    0.19
    /flutter
    0.19
     mingle
    0.19
     getStatus
    0.18
    aut
    0.18
    \-
    0.18
     roleName
    0.18
    Activations Density 5.725%

    No Known Activations