© 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. 2161
    Prev
    Next
    INDEX
    Explanations

    emails and names

    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
    ünün
    -0.25
     bordel
    -0.22
     (!((
    -0.21
    ÅĿ
    -0.21
    åŃ£åIJİ
    -0.21
    糣
    -0.21
    '=>"
    -0.20
    =findViewById
    -0.19
     GÅĤówn
    -0.19
    Breadcrumb
    -0.19
    POSITIVE LOGITS
    ëĶķ
    0.21
    éĢĤ
    0.21
     Y
    0.20
    -Assad
    0.20
    annie
    0.19
    =$((
    0.19
    .mi
    0.19
    .WindowManager
    0.19
    avern
    0.19
    åħ¶ä»ĸçݩ家
    0.19
    Activations Density 0.622%

    No Known Activations