© 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. 123
    Prev
    Next
    INDEX
    Explanations

    mathematical problems

    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
    ðŁĵIJ
    -0.41
    âļĹ
    -0.39
    âĮĤ
    -0.33
    /↵↵↵↵
    -0.31
     createState
    -0.31
    ðŁĵĻ
    -0.31
     (*((
    -0.31
    ].'
    -0.28
    ðŁĮ°
    -0.28
    /MIT
    -0.28
    POSITIVE LOGITS
    âŁ¹
    0.31
    åIJ©
    0.26
    纰
    0.25
    éĢłåģĩ
    0.25
    çĸł
    0.25
    åħ¶å®ĥéĹ®é¢ĺ
    0.24
     na
    0.24
    é»ijæģ¶
    0.23
    æĪķ
    0.23
    举äºļ
    0.23
    Activations Density 0.910%

    No Known Activations