© 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. 28
    Prev
    Next
    INDEX
    Explanations

    see

    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
    ä½łçŁ¥éģĵ
    -0.24
    memberof
    -0.21
     NavLink
    -0.21
    æĪijçŁ¥éģĵ
    -0.21
    åħ³äºİæĪij们
    -0.20
    çľĭä¸Ĭåİ»
    -0.20
     jihadist
    -0.19
     especÃŃfico
    -0.19
     //}↵↵
    -0.18
    ispens
    -0.18
    POSITIVE LOGITS
    /he
    0.29
    ä¸Ģçľ¼
    0.29
    {return
    0.28
    踪
    0.26
     ());↵↵
    0.26
    (fabs
    0.25
    rippling
    0.25
    "value
    0.25
    -Compatible
    0.25
    /read
    0.24
    Activations Density 2.544%

    No Known Activations