© 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. 3908
    Prev
    Next
    INDEX
    Explanations

    code or technical

    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
     ?>&
    -0.20
    é£Ĺ
    -0.20
    .AF
    -0.20
    ä»ī
    -0.20
    orgeous
    -0.20
    ìŀ¡
    -0.20
     atIndex
    -0.19
    åķĨä¼ļ
    -0.19
    æIJ¦
    -0.19
     fragmentManager
    -0.19
    POSITIVE LOGITS
    ={"/
    0.23
    Ëĥ
    0.22
    .kotlin
    0.21
    ={$
    0.21
    ABCDEFGHIJKLMNOP
    0.20
    .Serve
    0.20
    å§Ķç»Ħç»ĩ
    0.19
    bindings
    0.19
     Lif
    0.19
    äll
    0.18
    Activations Density 0.001%

    No Known Activations