© 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. 435
    Prev
    Next
    INDEX
    Explanations

    code or programming

    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
     acompaña
    -0.26
     semiclass
    -0.26
    éļĨéĩį举è¡Į
    -0.25
    NavController
    -0.25
    <stdlib
    -0.24
    NavLink
    -0.23
     Authenticate
    -0.23
    ChangeEvent
    -0.23
    ActionCreators
    -0.22
     erotica
    -0.22
    POSITIVE LOGITS
    ç½ijç«Ļé¦ĸ页
    0.31
    :disable
    0.28
    reactstrap
    0.27
    EXTERN
    0.26
    ä¸įåħĭ
    0.25
    )))));↵
    0.24
    .with
    0.24
    åĭį
    0.24
    			č↵			č↵
    0.24
    [href
    0.23
    Activations Density 2.976%

    No Known Activations