© 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. 3848
    Prev
    Next
    INDEX
    Explanations

    technical or code fragments

    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
    asn
    -0.24
    âĩij
    -0.23
    yı
    -0.20
    æľ¬äºĭ
    -0.20
    defgroup
    -0.20
    ìķŀ
    -0.20
    opard
    -0.19
     stringWithFormat
    -0.19
    ä¸ĩåħ¬éĩĮ
    -0.19
    èĵĬ
    -0.19
    POSITIVE LOGITS
    åĹľ
    0.21
    #ab
    0.21
     ×Ķ×ķ×ĵ
    0.21
    mania
    0.20
    .$.
    0.20
    иÑĤелÑĮн
    0.20
    åĽŁ
    0.18
    thinkable
    0.18
    кÑĥлÑĮÑĤ
    0.18
    ÙħÙĨØ°
    0.18
    Activations Density 0.001%

    No Known Activations