© 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. 4028
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
     ());↵↵
    -0.22
    æĹıèĩªæ²»
    -0.22
    /rfc
    -0.21
    _KeyPress
    -0.20
    家éĥ½çŁ¥éģĵ
    -0.19
    .US
    -0.19
    å¤ļéĩį
    -0.19
    å¸Ń
    -0.19
    ï¼ģ",
    -0.19
    èŀ³
    -0.19
    POSITIVE LOGITS
    egov
    0.26
     beneficiation
    0.22
     neighb
    0.22
     SharedModule
    0.20
    entiful
    0.20
    erialization
    0.19
    rone
    0.19
     masturbating
    0.19
    itmap
    0.19
    stdbool
    0.19
    Activations Density 0.000%

    No Known Activations