© 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-CHAT-65K
    7. 45434
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    chanind/qwen2.5-7B-it-layer-20-saes/lmsys/matryoshka/k-100
    Prompts (Dashboard)
    16,384 prompts, 192 tokens each
    Dataset (Dashboard)
    chanind/lmsys-chat-1m-qwen-2.5
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    ?>↵↵↵
    -0.22
     )↵↵↵↵↵↵↵↵
    -0.21
    })();↵↵
    -0.21
    eworthy
    -0.20
    -scenes
    -0.20
    =sum
    -0.20
    CppType
    -0.20
    enance
    -0.19
     -->↵↵↵
    -0.19
    .AllowUser
    -0.19
    POSITIVE LOGITS
     buflen
    0.20
    åĵģæł¼
    0.18
    alyzed
    0.18
    IPAddress
    0.18
    GetPosition
    0.18
    .readdir
    0.18
    çĴ§
    0.18
    arie
    0.18
    NSMutableDictionary
    0.18
    ertiary
    0.18
    Activations Density 0.000%

    No Known Activations