© 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. 3129
    Prev
    Next
    INDEX
    Explanations

    time ranges

    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
    iets
    -0.23
    >NN
    -0.20
    enga
    -0.19
    ê²Ł
    -0.19
    enty
    -0.18
    ôn
    -0.18
    WithPath
    -0.18
    æģ¯æģ¯
    -0.18
    ');//
    -0.18
    getFullYear
    -0.18
    POSITIVE LOGITS
    èĩ³
    0.64
    ï½ŀ
    0.40
    åĪ°
    0.39
     èĩ
    0.35
    ãĢľ
    0.35
    ~
    0.33
    å¹´èĩ³
    0.30
    æľĪèĩ³
    0.29
    -to
    0.29
    âĪ½
    0.28
    Activations Density 0.500%

    No Known Activations