© 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. 885
    Prev
    Next
    INDEX
    Explanations

    numbers and code

    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
    }elseif
    -0.21
    =fopen
    -0.20
    .readFileSync
    -0.20
    oriously
    -0.20
    ForMember
    -0.20
    AutoSize
    -0.20
    IFORM
    -0.19
    CellValue
    -0.19
    çªģå¦Ĥåħ¶æĿ¥
    -0.19
    ESSAGE
    -0.19
    POSITIVE LOGITS
    ãİĿ
    0.24
    女æĢ§æľĭåıĭ
    0.23
    ì°©
    0.22
     èĭ¥è¦ģ
    0.20
    uncan
    0.20
    (*)(
    0.20
    ámara
    0.20
     (*)(
    0.20
     ErdoÄŁan
    0.19
     createState
    0.19
    Activations Density 0.625%

    No Known Activations