© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen2.5-7B-IT
    5. 20-MATRYOSHKA-65K
    7. 265
    Prev
    Next
    INDEX
    Explanations

    license

    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
    berra
    -0.27
    OfString
    -0.26
    rvine
    -0.24
    CellValue
    -0.24
    istring
    -0.23
    .ManyToMany
    -0.23
    ridged
    -0.23
    asurer
    -0.23
    ntl
    -0.22
    .EventQueue
    -0.22
    POSITIVE LOGITS
    ä»İæł¹æľ¬
    0.23
     blir
    0.23
    åĵªå®¶å¥½
    0.23
     ============================================================================↵
    0.22
    ï¼ģï¼ģ↵↵
    0.21
     ÐŀÑģобенно
    0.21
    æĺ³
    0.21
    offsetof
    0.20
    ï½ŀ↵↵
    0.20
    ********************************************************************************
    0.20
    Activations Density 4.305%

    No Known Activations