© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen2.5-7B-IT
    5. 20-MATRYOSHKA-65K
    7. 2816
    Prev
    Next
    INDEX
    Explanations

    Proper names

    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
    ç¹Ħ
    -0.22
    ç¿»
    -0.20
    çĶ¸
    -0.19
    éħ¢
    -0.19
     migliori
    -0.19
    CardBody
    -0.19
    åĪĨæĪIJ
    -0.19
    аблиÑĨ
    -0.18
    åij¼åIJ¸
    -0.18
    ules
    -0.18
    POSITIVE LOGITS
    orgeous
    0.25
    }elseif
    0.23
    iage
    0.22
    å¢Ģ
    0.21
    :white
    0.21
     Programm
    0.20
    :inline
    0.20
    toPromise
    0.20
    :path
    0.20
    <path
    0.20
    Activations Density 0.010%

    No Known Activations