© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen2.5-7B-IT
    5. 20-MATRYOSHKA-65K
    7. 3285
    Prev
    Next
    INDEX
    Explanations

    technical or informational snippets

    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
    ifestyles
    -0.20
    akest
    -0.20
     sidl
    -0.19
    itori
    -0.19
    yd
    -0.19
    å¨ł
    -0.19
    efeller
    -0.19
     JpaRepository
    -0.19
    HttpServletRequest
    -0.19
    ि
    -0.18
    POSITIVE LOGITS
    orgeous
    0.21
    (defvar
    0.20
    .AddTransient
    0.19
    addle
    0.19
    æ»ĺ
    0.19
     Seit
    0.18
     subsid
    0.18
    ono
    0.18
    ]++;↵
    0.18
    .removeEventListener
    0.17
    Activations Density 0.001%

    No Known Activations