© 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. 3943
    Prev
    Next
    INDEX
    Explanations

    side

    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
    ä¸ĵåĮº
    -0.22
    ä¾ĭå¤ĸ
    -0.19
    iasm
    -0.19
    =?";↵
    -0.19
    CCCCCC
    -0.19
     ire
    -0.19
     topLeft
    -0.18
    ÙĬب
    -0.18
    iii
    -0.18
     شأÙĨ
    -0.18
    POSITIVE LOGITS
    åģ´
    0.34
     side
    0.33
    ä¸Ģ侧
    0.31
    -side
    0.31
     sides
    0.30
     ÑģÑĤоÑĢо
    0.28
     Side
    0.27
     half
    0.27
    _side
    0.27
    ä¸Ģæĸ¹
    0.27
    Activations Density 0.347%

    No Known Activations