© 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. 293
    Prev
    Next
    INDEX
    Explanations

    quantity

    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
    rouch
    -0.24
    ç¨į
    -0.23
    minent
    -0.19
    ç¨įå¾®
    -0.19
     slightly
    -0.18
    ﹩
    -0.18
    adel
    -0.18
    aten
    -0.18
    brief
    -0.18
    .ibatis
    -0.17
    POSITIVE LOGITS
     (>
    0.34
    ToMany
    0.24
     amount
    0.24
     amounts
    0.24
    plr
    0.24
     mẽ
    0.22
    æ¶Įåħ¥
    0.22
    -many
    0.21
    æ¶Įçİ°
    0.21
    avaÅŁ
    0.21
    Activations Density 3.708%

    No Known Activations