© 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. 770
    Prev
    Next
    INDEX
    Explanations

    technical fragments

    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
     enthus
    -0.27
    berra
    -0.25
    NavLink
    -0.22
     Wrest
    -0.22
    phalt
    -0.22
    iben
    -0.22
    irical
    -0.21
    icularly
    -0.21
     annunci
    -0.21
    apgolly
    -0.21
    POSITIVE LOGITS
     (*((
    0.24
    åĪ©çĶ¨æĤ¨çļĦ
    0.20
     particulière
    0.20
    æĵ¤
    0.19
    æģ«
    0.19
    æĪķ
    0.19
     ((__
    0.19
     Geb
    0.18
    .Never
    0.18
    ("("
    0.18
    Activations Density 4.775%

    No Known Activations