© 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. 1972
    Prev
    Next
    INDEX
    Explanations

    numbers and quantities

    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
    çī¢è®°ä½¿åij½
    -0.25
    AndPassword
    -0.22
    çļĦ带é¢Ĩ
    -0.21
    .navigationBar
    -0.20
     "'.
    -0.20
     Goblin
    -0.19
    æľªæĪIJå¹´
    -0.19
    marginTop
    -0.19
    çĸł
    -0.18
    ;"><?
    -0.18
    POSITIVE LOGITS
    /↵↵↵↵
    0.27
    -peer
    0.25
    #ac
    0.25
    paralleled
    0.24
    ropri
    0.23
    erguson
    0.23
    prech
    0.23
    byname
    0.23
    ivitÃł
    0.23
    \Id
    0.22
    Activations Density 0.431%

    No Known Activations