© 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. 250
    Prev
    Next
    INDEX
    Explanations

    technical 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
    çī©æµģåħ¬åı¸
    -0.21
    preci
    -0.21
    mue
    -0.19
    -feed
    -0.19
     ARISING
    -0.19
    amp
    -0.19
     landing
    -0.18
    æĢł
    -0.18
     Roe
    -0.18
    ä¼Ļä¼´åħ³ç³»
    -0.18
    POSITIVE LOGITS
    )test
    0.23
    clado
    0.23
    []=$
    0.22
    âķ¯
    0.22
     POLITICO
    0.22
    æĸ°æµªè´¢ç»ı
    0.22
     koje
    0.22
    /xhtml
    0.22
    ButtonTitles
    0.21
    piler
    0.21
    Activations Density 0.001%

    No Known Activations