© 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. 2769
    Prev
    Next
    INDEX
    Explanations

    technical project dates

    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
    èĥĹ
    -0.23
    spir
    -0.22
    ccoli
    -0.21
     mooie
    -0.21
    ');?>"
    -0.20
    游æĪıè§Ĵèī²
    -0.20
     ÐijеÑģ
    -0.19
    åħįè´£
    -0.19
    æĬ±ä½ı
    -0.19
    èľī
    -0.19
    POSITIVE LOGITS
     ($("#
    0.21
    ;br
    0.21
     dun
    0.20
     misd
    0.20
    :NS
    0.20
    declspec
    0.20
     ($('#
    0.19
    ERTICAL
    0.19
    .navigationItem
    0.19
    lion
    0.18
    Activations Density 0.001%

    No Known Activations