© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen2.5-7B-IT
    5. 20-MATRYOSHKA-65K
    7. 1334
    Prev
    Next
    INDEX
    Explanations

    tools

    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
     scarc
    -0.37
     acompaña
    -0.33
     misog
    -0.30
    èħĺ
    -0.29
     bât
    -0.29
     hairst
    -0.28
     bbc
    -0.28
     seiz
    -0.27
    缸åħ³è´Łè´£
    -0.26
     pestic
    -0.26
    POSITIVE LOGITS
     lokale
    0.30
    ."&
    0.30
    ")));
    0.30
    -Token
    0.30
    "),"
    0.29
    foundland
    0.28
    %M
    0.28
    .'<
    0.28
    )(*
    0.28
    -Origin
    0.28
    Activations Density 10.832%

    No Known Activations