© 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. 607
    Prev
    Next
    INDEX
    Explanations

    St

    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
    DMETHOD
    -0.51
     Interracial
    -0.45
    curacy
    -0.40
    lke
    -0.37
    зÑĭва
    -0.36
    ForMember
    -0.35
     Millenn
    -0.35
    "';
    -0.34
    rary
    -0.34
    usterity
    -0.34
    POSITIVE LOGITS
     bada
    0.32
     rej
    0.30
     hud
    0.28
     roma
    0.26
     yab
    0.26
     nouve
    0.26
     tou
    0.26
     cerco
    0.25
    ewart
    0.25
    on
    0.24
    Activations Density 6.628%

    No Known Activations