© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen2.5-7B-IT
    5. 20-MATRYOSHKA-65K
    7. 3182
    Prev
    Next
    INDEX
    Explanations

    number or count

    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
     didSelectRowAtIndexPath
    -0.23
    éļĶ
    -0.20
    ):?>↵
    -0.20
     avalia
    -0.20
     buz
    -0.19
    åħ³äºİæĪij们
    -0.19
    åı£æ°Ķ
    -0.19
    人群
    -0.19
    è¿Ļéĥ¨åĪĨ
    -0.19
    hread
    -0.18
    POSITIVE LOGITS
    æĢ»æķ°
    0.39
    æķ°éĩı
    0.39
    æķ°
    0.39
     number
    0.36
     count
    0.36
    æķ°çĽ®
    0.36
    _count
    0.35
    count
    0.33
     Count
    0.32
    -count
    0.32
    Activations Density 0.772%

    No Known Activations