© 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. 1594
    Prev
    Next
    INDEX
    Explanations

    say "number digits"

    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
    æ·±åĮĸæĶ¹éĿ©
    -0.25
    èħ©
    -0.24
     fas
    -0.22
    \Array
    -0.21
    äºĨ解ä¸Ģä¸ĭ
    -0.21
     terminal
    -0.21
    terminal
    -0.20
    па
    -0.20
    åīį身
    -0.20
    paused
    -0.20
    POSITIVE LOGITS
    /DD
    0.21
    åĿļå®ļä¸į
    0.21
    æ¾
    0.21
    _idxs
    0.20
    /↵↵↵↵
    0.20
     Según
    0.20
     Rooney
    0.19
    utenberg
    0.19
    stantiateViewController
    0.19
    LOCKS
    0.19
    Activations Density 0.015%

    No Known Activations