© 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. 3023
    Prev
    Next
    INDEX
    Explanations

    essentials

    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
    Not in Any Lists

    No Comments

    Negative Logits
    uckland
    -0.27
    |required
    -0.24
    rvine
    -0.22
    íĶĦë¡ľê·¸
    -0.22
    crast
    -0.20
     TOK
    -0.19
    }elseif
    -0.19
    byss
    -0.18
    ä¸ĢæľŁ
    -0.18
    ç½²
    -0.18
    POSITIVE LOGITS
     manh
    0.25
    CISION
    0.22
    grily
    0.21
    HITE
    0.21
    .)↵↵↵↵
    0.20
    s
    0.20
    	↵	↵↵
    0.20
    orgeous
    0.19
    avanaugh
    0.19
    rna
    0.19
    Activations Density 1.059%

    No Known Activations