© 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. 3951
    Prev
    Next
    INDEX
    Explanations

    UI/GUI

    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
    alink
    -0.20
    Türkiye
    -0.20
    æ¸İ
    -0.19
    çĬŁ
    -0.19
    processable
    -0.19
     illum
    -0.19
    viders
    -0.18
    PTH
    -0.18
    ฿
    -0.18
    DrawerToggle
    -0.18
    POSITIVE LOGITS
     Kardash
    0.23
    kea
    0.23
     cellForRowAt
    0.21
     Boat
    0.20
     acompaña
    0.20
     masturb
    0.20
     sublic
    0.20
    ivant
    0.20
    ilogy
    0.19
    elder
    0.19
    Activations Density 0.726%

    No Known Activations