© 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. 1987
    Prev
    Next
    INDEX
    Explanations

    death

    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
    avenport
    -0.24
     thugs
    -0.21
     LoginActivity
    -0.20
    满
    -0.19
     coraz
    -0.19
     gunmen
    -0.18
     inds
    -0.18
     Ron
    -0.18
    0
    -0.18
    éļħ
    -0.18
    POSITIVE LOGITS
    ä¸Ģèĩ´å¥½è¯Ħ
    0.30
    âĦī
    0.28
    åĭł
    0.25
    âļĹ
    0.25
    ðŁĵIJ
    0.25
    }$/
    0.24
    .getOwnProperty
    0.24
    +");↵
    0.24
    prowad
    0.24
    åĪ©çĶ¨æĤ¨çļĦ
    0.24
    Activations Density 2.335%

    No Known Activations