© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen2.5-7B-IT
    5. 20-MATRYOSHKA-65K
    7. 610
    Prev
    Next
    INDEX
    Explanations

    identifiers and topics

    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
    /Dk
    -0.25
    licted
    -0.24
     }):
    -0.22
    æĹłæīĢ
    -0.22
     libertin
    -0.21
     tü
    -0.21
    .RELATED
    -0.20
    IsRequired
    -0.20
    ->[
    -0.20
    *);↵↵
    -0.20
    POSITIVE LOGITS
    åľ¨è¿ĩ渡
    0.22
     Fro
    0.19
    ableObject
    0.18
     unw
    0.18
     åį
    0.18
    Compose
    0.18
    rä
    0.18
    ieder
    0.18
    é»ij
    0.17
    enco
    0.17
    Activations Density 0.001%

    No Known Activations