© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen2.5-7B-IT
    5. 20-MATRYOSHKA-65K
    7. 511
    Prev
    Next
    INDEX
    Explanations

    biological functions

    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
    ä»ħ代表
    -0.27
    æĤ
    -0.26
    ivre
    -0.23
     consulate
    -0.22
    é¢Ģ
    -0.21
    -datepicker
    -0.21
    èħł
    -0.20
    迹
    -0.20
     Administration
    -0.20
    nodeName
    -0.20
    POSITIVE LOGITS
     function
    0.26
     struct
    0.24
    çļĦåĬŁèĥ½
    0.24
    åĬŁèĥ½
    0.23
     functions
    0.22
    è°ĥæݧ
    0.22
    hores
    0.21
     semiclass
    0.21
     ÑĦÑĥнкÑĨи
    0.21
    è¡Į使
    0.20
    Activations Density 4.860%

    No Known Activations