© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen2.5-7B-IT
    5. 20-MATRYOSHKA-65K
    7. 4373
    Prev
    Next
    INDEX
    Explanations

    privacy, sensitive

    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
    Negative Logits
    engeance
    -0.25
     Bek
    -0.21
    éĢģè¾¾
    -0.21
    津贴
    -0.20
    ASN
    -0.20
    .ValidationError
    -0.19
    ILLISECONDS
    -0.19
    çIJĨ解åĴĮ
    -0.19
    NullException
    -0.19
    xDE
    -0.18
    POSITIVE LOGITS
    æķıæĦŁ
    0.29
     sensitive
    0.28
    æķı
    0.25
    éļIJç§ģ
    0.25
    -sensitive
    0.24
     privacy
    0.24
    ä¿¡æģ¯å®īåħ¨
    0.24
    privacy
    0.22
    Sensitive
    0.21
    raits
    0.21
    Activations Density 0.156%

    No Known Activations