© 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. 415
    Prev
    Next
    INDEX
    Explanations

    learning technical terms

    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
     gratuitement
    -0.23
    ä¸Ģèĩ´å¥½è¯Ħ
    -0.23
     Sofa
    -0.23
    byss
    -0.22
    æ¹İ
    -0.22
    rypton
    -0.22
    esteem
    -0.21
    stdarg
    -0.21
    å±Ĥåĩºä¸į
    -0.21
    :"",↵
    -0.21
    POSITIVE LOGITS
    IALOG
    0.24
    ulings
    0.23
    variably
    0.22
    bsolute
    0.22
    rchive
    0.21
    chedulers
    0.21
    eor
    0.20
    errated
    0.20
    exampleInputEmail
    0.20
    emailer
    0.20
    Activations Density 7.335%

    No Known Activations