© 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. 2735
    Prev
    Next
    INDEX
    Explanations

    word fragments

    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
    游æĪıæĬĢå·§
    -0.26
    BUFF
    -0.23
    PIP
    -0.23
    游æĪıæĵįä½ľ
    -0.22
    "path
    -0.20
    Toolkit
    -0.20
    владе
    -0.20
    å¾Īå¤ļçݩ家
    -0.20
    .Ordinal
    -0.19
    åħ¨åĬĽä»¥
    -0.19
    POSITIVE LOGITS
    idepress
    0.25
    urances
    0.22
    etz
    0.22
    (strpos
    0.20
    igner
    0.20
    аÑĤÑĥÑĢ
    0.20
     paddingRight
    0.19
    ена
    0.19
    .getEnd
    0.19
    ardown
    0.19
    Activations Density 0.001%

    No Known Activations