© 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. 2544
    Prev
    Next
    INDEX
    Explanations

    code

    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
    :result
    -0.26
    alyzed
    -0.25
    aceut
    -0.24
    isObject
    -0.23
    oriously
    -0.23
    ornment
    -0.22
    hế
    -0.21
    isos
    -0.20
    ApiController
    -0.20
    ancode
    -0.20
    POSITIVE LOGITS
    обеÑģп
    0.26
    ç½ijç«Ļé¦ĸ页
    0.25
     elek
    0.24
     vak
    0.23
     rekl
    0.23
    æĢ§ä»·
    0.23
    åľ¨è¿ĩ渡
    0.23
     gere
    0.22
     ×Ķ×ķ×ĵ
    0.22
    Ó¨
    0.22
    Activations Density 0.017%

    No Known Activations