© 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. 2760
    Prev
    Next
    INDEX
    Explanations

    mathematical functions and variables

    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
    Calibri
    -0.28
    @update
    -0.26
    __["
    -0.24
    .BLL
    -0.23
    ditor
    -0.23
    hế
    -0.22
    iá»ĩu
    -0.22
    #ga
    -0.22
    @store
    -0.22
    æ¦ī
    -0.22
    POSITIVE LOGITS
    ç¥ĸ
    0.20
    èħ´
    0.19
    ä¸İæŶ
    0.19
     ancestral
    0.18
    æīģ
    0.18
    修士
    0.18
    è¿ŀæİ¥
    0.18
    对æѤ
    0.18
     findAll
    0.17
     peripherals
    0.17
    Activations Density 0.025%

    No Known Activations