© 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. 151
    Prev
    Next
    INDEX
    Explanations

    legal documents

    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
    /compiler
    -0.21
    -animate
    -0.20
    年产åĢ¼
    -0.19
     textSize
    -0.19
    æĥ´
    -0.19
    åıĭæĥħéĵ¾æİ¥
    -0.19
    InstanceOf
    -0.19
    èµĢ
    -0.18
    .caption
    -0.18
    .Pages
    -0.18
    POSITIVE LOGITS
    æł¹æį®
    0.24
    .AutoScaleMode
    0.23
    ({...
    0.22
    âĸİ
    0.20
    èħ§
    0.20
    CppClass
    0.20
    è§ģéĿ¢
    0.20
    .fromRGBO
    0.20
    +='<
    0.20
    puties
    0.20
    Activations Density 0.601%

    No Known Activations