© 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. 535
    Prev
    Next
    INDEX
    Explanations

    diverse/technical language

    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
     rekl
    -0.33
    欢è¿İæĤ¨
    -0.30
    å°±ç»Ļ大家
    -0.29
     Müsl
    -0.29
     uda
    -0.28
     Khá
    -0.27
     kaps
    -0.27
    ðŁ¥ĩ
    -0.26
    Gratis
    -0.25
     kup
    -0.25
    POSITIVE LOGITS
     masturbating
    0.28
    çļĦ带é¢Ĩ
    0.25
     tantra
    0.24
     suede
    0.23
    _transaksi
    0.23
     millenn
    0.23
     OnCollision
    0.23
     FixedUpdate
    0.22
     véhicule
    0.22
    ancock
    0.22
    Activations Density 0.396%

    No Known Activations