© 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. 1210
    Prev
    Next
    INDEX
    Explanations

    Use

    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
    ulfill
    -0.23
    أخر
    -0.21
    rypton
    -0.21
     Pistons
    -0.21
    è´¸æĺĵæĪĺ
    -0.21
     Erotic
    -0.20
    ($('<
    -0.20
     Interracial
    -0.20
    à¸ģารà¸Ĺำà¸ĩาà¸Ļ
    -0.20
    =require
    -0.20
    POSITIVE LOGITS
    fully
    0.30
     techniques
    0.25
    raig
    0.24
     Gòn
    0.24
    è¿Ļç§įæĸ¹æ³ķ
    0.23
    ÙĨتائ
    0.23
    DonaldTrump
    0.23
    fulness
    0.23
    ocht
    0.22
    bish
    0.22
    Activations Density 1.749%

    No Known Activations