© 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. 1248
    Prev
    Next
    INDEX
    Explanations

    locations

    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
    _Tick
    -0.24
     verm
    -0.23
    ä¼ŀ
    -0.22
    ();++
    -0.21
    ìĪ¨
    -0.19
     masturbating
    -0.19
    yth
    -0.18
    }elseif
    -0.18
    DMETHOD
    -0.18
    ineTransform
    -0.18
    POSITIVE LOGITS
     Leer
    0.22
     ×Ķ×ķ×ĵ
    0.21
    æĵIJ
    0.21
    %!
    0.20
    ëIJ¬
    0.19
     ÙĬÙĪس
    0.19
    ionales
    0.19
    oser
    0.19
     PÃ¥
    0.19
    вÑĪие
    0.19
    Activations Density 0.001%

    No Known Activations