© 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. 581
    Prev
    Next
    INDEX
    Explanations

    results and theorems

    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
     ++)
    -0.28
    aeper
    -0.26
    -Feb
    -0.25
     meiden
    -0.24
    {//
    -0.24
    (*)(
    -0.24
    /Register
    -0.24
    )index
    -0.23
    *)_
    -0.23
    ,www
    -0.23
    POSITIVE LOGITS
    è¯ģæĺİ
    0.30
     proved
    0.27
     property
    0.25
     condition
    0.25
     statement
    0.25
    ($(".
    0.24
     proof
    0.23
     conditions
    0.23
     assertion
    0.23
     easily
    0.23
    Activations Density 0.408%

    No Known Activations