© 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. 3958
    Prev
    Next
    INDEX
    Explanations

    technical or science

    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
    ivant
    -0.22
    AXB
    -0.21
     stripslashes
    -0.21
    对åħ¶çľŁå®ŀ
    -0.21
    -mf
    -0.21
    =-=-=-=-
    -0.21
    puties
    -0.21
    ificate
    -0.21
    kaza
    -0.20
    úb
    -0.20
    POSITIVE LOGITS
     {.
    0.24
     impart
    0.20
    é¹Ĭ
    0.19
    ãĥĿãĤ¤
    0.19
    irlines
    0.19
     Liter
    0.18
     tang
    0.18
    QUIRE
    0.18
    æİ·
    0.18
    odiac
    0.17
    Activations Density 0.001%

    No Known Activations