© 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. 3122
    Prev
    Next
    INDEX
    Explanations

    technical/scientific topics

    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
    *pow
    -0.22
    *scale
    -0.22
    pson
    -0.22
    odynam
    -0.21
    ****/↵
    -0.21
    ä¹¾
    -0.20
     intox
    -0.19
    egot
    -0.19
    ItemClick
    -0.19
    .DataAccess
    -0.19
    POSITIVE LOGITS
     shift
    0.20
     )↵↵↵↵↵↵↵↵
    0.20
     ApplicationDbContext
    0.19
     subs
    0.19
     Shift
    0.19
     shifts
    0.18
    prenom
    0.18
    主åĬ¨æĢ§
    0.18
    _SUITE
    0.18
    鼶éĥ¨ä»¶
    0.18
    Activations Density 0.002%

    No Known Activations