© 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. 1558
    Prev
    Next
    INDEX
    Explanations

    code keywords

    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
     strugg
    -0.27
     consc
    -0.27
     impecc
    -0.26
     Kardash
    -0.24
    ábado
    -0.23
     incons
    -0.23
    å±ŀäºİèĩªå·±
    -0.23
     pestic
    -0.23
     desar
    -0.22
    åŬ
    -0.22
    POSITIVE LOGITS
    etheless
    0.21
     coppia
    0.21
    Hôtel
    0.20
     Gründe
    0.19
    çł°
    0.19
    alyzed
    0.19
    æ²®
    0.19
    .Does
    0.19
    æģļ
    0.18
    .Compare
    0.18
    Activations Density 3.284%

    No Known Activations