© 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. 2657
    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
     }])↵
    -0.25
    поÑĩÑĤ
    -0.24
    ermen
    -0.21
    longleftrightarrow
    -0.20
    ++]=
    -0.19
    ngle
    -0.19
    izador
    -0.19
    perate
    -0.19
    ';↵↵↵↵
    -0.19
    GEST
    -0.19
    POSITIVE LOGITS
    缣
    0.22
    åĵªå®¶å¥½
    0.21
    å³Ļ
    0.21
    ä¹Įåħĭ
    0.20
    âĦī
    0.20
    éĵij
    0.20
    æĥķ
    0.19
    à¸ĵ
    0.19
    upa
    0.19
    دÙĪا
    0.18
    Activations Density 0.000%

    No Known Activations