© 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. 1660
    Prev
    Next
    INDEX
    Explanations

    Names and entities

    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¿«
    -0.21
    importDefault
    -0.21
    ĩ
    -0.20
    æ³ķå¸ĪèģĮä¸ļ
    -0.20
    wij
    -0.20
     anál
    -0.20
    æĪĺ士èģĮä¸ļ
    -0.19
    åĢ¦
    -0.19
    /OR
    -0.19
     hete
    -0.18
    POSITIVE LOGITS
    WithPath
    0.22
    ntax
    0.22
    WithType
    0.21
    indsay
    0.21
    stroy
    0.21
    essim
    0.20
    ungalow
    0.20
    <source
    0.20
    utenberg
    0.19
    antt
    0.19
    Activations Density 0.009%

    No Known Activations