© 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. 2405
    Prev
    Next
    INDEX
    Explanations

    document snippets

    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
    ofile
    -0.20
    ][/
    -0.20
    -scalable
    -0.20
    èĽ®
    -0.19
    ILLED
    -0.19
    ï¼ĩ
    -0.19
    æĹĥ
    -0.19
    åIJ¬è¯Ŀ
    -0.18
    èħ¾é£ŀ
    -0.18
    ,...↵
    -0.18
    POSITIVE LOGITS
    plaint
    0.23
    arrants
    0.22
    xfff
    0.21
    aupt
    0.21
    anford
    0.21
     démarch
    0.20
     Lesb
    0.19
    asthan
    0.19
    æģ¤
    0.19
    elfare
    0.19
    Activations Density 0.011%

    No Known Activations