© 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. 2465
    Prev
    Next
    INDEX
    Explanations

    technical fragments

    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
     cerco
    -0.31
    æŁ¥çľĭ详æĥħ
    -0.31
     threesome
    -0.31
    'gc
    -0.28
     fierc
    -0.26
    åĬĽè¿ĺæĺ¯
    -0.26
     fucks
    -0.26
    对çħ§æ£ĢæŁ¥
    -0.26
     pione
    -0.25
     diseñador
    -0.25
    POSITIVE LOGITS
    urgy
    0.28
    Uvs
    0.25
    itmap
    0.24
    izontal
    0.24
     manh
    0.24
    ">'.
    0.24
    serter
    0.24
    ">ÃĹ</
    0.23
    endereco
    0.23
    .Designer
    0.23
    Activations Density 8.256%

    No Known Activations