© 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. 2318
    Prev
    Next
    INDEX
    Explanations

    microRNA

    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
    èµİ
    -0.23
    alach
    -0.22
    знаком
    -0.21
    åĢĴåľ¨åľ°
    -0.20
    <Sprite
    -0.20
    rames
    -0.20
    ibraltar
    -0.20
    ictory
    -0.19
    åĴİ
    -0.19
    .componentInstance
    -0.19
    POSITIVE LOGITS
     mies
    0.22
    RNA
    0.21
    CppType
    0.21
     dames
    0.21
     "','
    0.20
    åŃ
    0.20
     näm
    0.20
    saldo
    0.19
     zak
    0.19
    ØŃÙĤ
    0.19
    Activations Density 0.144%

    No Known Activations