© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen2.5-7B-IT
    5. 20-MATRYOSHKA-65K
    7. 1347
    Prev
    Next
    INDEX
    Explanations

    structural markers

    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
    коло
    -0.22
     Genç
    -0.21
    çķĽ
    -0.20
     ноÑı
    -0.20
    å»ĵ
    -0.20
     flush
    -0.19
    å¾Īå¤ļçݩ家
    -0.19
    amacare
    -0.18
    å®ĭä½ĵ
    -0.18
    !important
    -0.18
    POSITIVE LOGITS
     WARRANT
    0.22
    atomy
    0.21
    |=↵
    0.21
    rif
    0.19
    asmine
    0.18
    inerary
    0.18
     McDon
    0.18
    interp
    0.18
    éªī
    0.18
     rootView
    0.18
    Activations Density 0.002%

    No Known Activations