© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen2.5-7B-IT
    5. 20-MATRYOSHKA-65K
    7. 3999
    Prev
    Next
    INDEX
    Explanations

    text processing

    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
    /////
    -0.25
    ðŁĻĤ
    -0.23
    =@"
    -0.23
    incinn
    -0.23
    Wunused
    -0.23
    gre
    -0.22
    procs
    -0.21
    )view
    -0.21
    oplayer
    -0.21
    tü
    -0.21
    POSITIVE LOGITS
     rencont
    0.23
    itation
    0.19
    ä¸Ģè¡Į
    0.19
     communic
    0.19
     maté
    0.18
    ispens
    0.18
    é«ģ
    0.18
     maç
    0.18
    MatrixMode
    0.18
     Dane
    0.18
    Activations Density 0.001%

    No Known Activations