© 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. 1943
    Prev
    Next
    INDEX
    Explanations

    technical terms

    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
    _detalle
    -0.23
    DateString
    -0.23
     ?>/
    -0.22
    çݩ家们
    -0.22
    ä»ħ代表
    -0.22
    :animated
    -0.21
     arguably
    -0.20
    èŁª
    -0.20
    neapolis
    -0.20
     OnePlus
    -0.20
    POSITIVE LOGITS
     acompaña
    0.28
    åĺīå¹´
    0.28
     semiclass
    0.26
     novitÃł
    0.25
     coppia
    0.23
    úsqueda
    0.23
     bénéficie
    0.23
    æŶéļĶ
    0.22
     modalitÃł
    0.21
    Fal
    0.21
    Activations Density 2.532%

    No Known Activations