© 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. 3083
    Prev
    Next
    INDEX
    Explanations

    quantification and variables

    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
     Å¡to
    -0.24
     avaliações
    -0.21
     Pend
    -0.21
     Dough
    -0.20
     deser
    -0.20
    phalt
    -0.19
     kako
    -0.19
    berra
    -0.19
     OnTrigger
    -0.19
    движ
    -0.19
    POSITIVE LOGITS
    大åŀĭå¤ļ人
    0.21
     MetroFramework
    0.20
     CHARSET
    0.20
    è¦ģ好好
    0.20
    äºĨåįĬ天
    0.19
    èİľ
    0.19
    ë¹Į
    0.19
    æĬĶ
    0.18
    ?("
    0.18
    以èī²
    0.18
    Activations Density 0.022%

    No Known Activations