© 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. 284
    Prev
    Next
    INDEX
    Explanations

    code and repositories

    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
    åıĪ好åıĪå¿«
    -0.25
    buah
    -0.24
    åĭł
    -0.24
    uries
    -0.22
    åħļæĢ»
    -0.21
     Westbrook
    -0.20
    vla
    -0.20
    åıĭæĥħéĵ¾æİ¥
    -0.20
    SingleOrDefault
    -0.20
    immers
    -0.20
    POSITIVE LOGITS
    å¾Ń
    0.20
    _hooks
    0.20
    å¹´ä¹ĭ
    0.20
     minHeight
    0.19
    å¹´ä¹ĭä¹ħ
    0.19
     "}↵
    0.19
    обÑĭÑĤи
    0.19
    èĴ
    0.18
     minWidth
    0.18
    踵
    0.18
    Activations Density 2.951%

    No Known Activations