© 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. 1552
    Prev
    Next
    INDEX
    Explanations

    specific identifiers

    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
    >{!!
    -0.24
    ÑĪим
    -0.24
    conexao
    -0.21
    )const
    -0.20
    upakan
    -0.20
    stants
    -0.19
     både
    -0.19
    æı´
    -0.19
    è¢ĸ
    -0.18
    ç¶ļãģįãĤĴèªŃãĤĢ
    -0.18
    POSITIVE LOGITS
    eltas
    0.22
    erchant
    0.21
    utomation
    0.21
     blowjob
    0.19
     AndAlso
    0.19
    ðŁĺĢ
    0.19
    поÑĤенÑĨи
    0.19
    trys
    0.19
     anál
    0.18
    -Cs
    0.18
    Activations Density 0.001%

    No Known Activations