© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen2.5-7B-IT
    5. 20-MATRYOSHKA-65K
    7. 664
    Prev
    Next
    INDEX
    Explanations

    I

    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
    å¾Īå¤ļçݩ家
    -0.23
    arefa
    -0.23
    ethyst
    -0.22
    uchos
    -0.22
    .books
    -0.21
    å°±æĿ¥çľĭçľĭ
    -0.21
    #ad
    -0.21
    ){}↵
    -0.21
    篷
    -0.21
    宣称
    -0.21
    POSITIVE LOGITS
    建议
    0.27
     personally
    0.26
     Joi
    0.22
     refr
    0.21
     wides
    0.21
    建èŃ°
    0.20
    æĿľ
    0.20
     suggest
    0.20
    éķ¿å¯¿
    0.19
     ArtÃŃculo
    0.19
    Activations Density 1.281%

    No Known Activations