© 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. 3576
    Prev
    Next
    INDEX
    Explanations

    unit conversions

    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
    <small
    -0.24
    ahas
    -0.21
    /MPL
    -0.21
    mast
    -0.20
    rigesimal
    -0.20
    >{"
    -0.20
     BusinessException
    -0.20
    ético
    -0.20
    ë¹Ħìļ©
    -0.19
    kest
    -0.19
    POSITIVE LOGITS
    bindParam
    0.20
     }?>↵
    0.20
    замен
    0.20
     sockfd
    0.19
     PD
    0.19
     lança
    0.18
    stinence
    0.18
    und
    0.18
    çijķçĸµ
    0.18
    åħ¨äº§ä¸ļéĵ¾
    0.18
    Activations Density 0.006%

    No Known Activations