© 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. 3529
    Prev
    Next
    INDEX
    Explanations

    specific titles

    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
    emetery
    -0.21
    lore
    -0.20
    ordion
    -0.19
     McCart
    -0.19
    å¤Ħ
    -0.19
    ünün
    -0.19
    æħķ
    -0.19
    .netflix
    -0.18
    ocre
    -0.18
     barcelona
    -0.18
    POSITIVE LOGITS
    .'&
    0.24
     ?><
    0.23
    ."&
    0.23
    GORITH
    0.23
    onestly
    0.22
    ////////////////////////////////////////////////////
    0.21
    %M
    0.21
    )||(
    0.21
    迤
    0.21
    xea
    0.21
    Activations Density 0.005%

    No Known Activations