© 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. 1299
    Prev
    Next
    INDEX
    Explanations

    nowadays

    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
    Türkiye
    -0.29
     taco
    -0.28
    zcze
    -0.28
    viar
    -0.27
    _amt
    -0.27
     utilizing
    -0.27
    ------+------+
    -0.27
     ostensibly
    -0.26
    ÃľR
    -0.26
    -Methods
    -0.25
    POSITIVE LOGITS
    讵
    0.37
     «
    0.33
     nowadays
    0.32
     splitted
    0.31
    «
    0.30
     Nowadays
    0.30
     negoci
    0.29
     caracter
    0.28
     serie
    0.28
     equipments
    0.28
    Activations Density 10.178%

    No Known Activations