© 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. 3094
    Prev
    Next
    INDEX
    Explanations

    there

    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
    TOTYPE
    -0.27
    CLUDING
    -0.26
     POLITICO
    -0.23
    ourcem
    -0.23
    ););↵
    -0.23
     tats
    -0.23
    buch
    -0.23
    iferay
    -0.22
    oenix
    -0.22
    /Dk
    -0.22
    POSITIVE LOGITS
    ÑĢен
    0.22
    tridges
    0.21
    istringstream
    0.20
    éľĦ
    0.20
    éģĵ
    0.20
    ãĤĢ
    0.20
    apid
    0.19
    å¢ŀ
    0.19
    éĢĤåIJĪ
    0.19
    åIJ¯
    0.18
    Activations Density 0.010%

    No Known Activations