© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen2.5-7B-IT
    5. 20-MATRYOSHKA-65K
    7. 997
    Prev
    Next
    INDEX
    Explanations

    code programming concepts

    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
    -deals
    -0.27
    //=
    -0.27
    braska
    -0.23
    -redux
    -0.23
    chestra
    -0.23
    ornings
    -0.22
    []{↵
    -0.22
    :convert
    -0.22
    *)_
    -0.22
     */;↵
    -0.22
    POSITIVE LOGITS
    è¿Ļç§įäºĭæĥħ
    0.23
    åıĪ好åıĪå¿«
    0.23
    åİŁåĽłä¹ĭä¸Ģ
    0.23
    è´´åIJ§
    0.21
     sublic
    0.21
    åĩŃä»Ģä¹Ī
    0.21
    ä»İæł¹æľ¬
    0.21
    åı¯æĥ³
    0.21
     UClass
    0.21
     ifdef
    0.20
    Activations Density 1.351%

    No Known Activations