© 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. 3676
    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
    (nonatomic
    -0.25
    ä½ĵèĤ²å½©ç¥¨
    -0.24
    ADATA
    -0.21
    CREMENT
    -0.21
    ãĤľ
    -0.21
    ï¼ģ');↵
    -0.20
    \xaa
    -0.20
    æĿ¥çľĭçľĭåIJ§
    -0.19
    åıĸåĨ³
    -0.19
    èĩªä¸»åĵģçīĮ
    -0.19
    POSITIVE LOGITS
     burge
    0.25
    åıĮéĩį
    0.21
    dÃŃa
    0.20
     boyc
    0.20
    第ä¸Ģæī¹
    0.19
     gratuites
    0.19
    ä¸Ģæī¹
    0.19
    มาà¸ģà¹Ĩ
    0.19
    lashes
    0.19
     HeaderComponent
    0.19
    Activations Density 0.000%

    No Known Activations