© 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. 2214
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    .TabStop
    -0.22
    entiful
    -0.22
    ']!='
    -0.21
    妤
    -0.21
    æī«ä¸Ģæī«
    -0.20
    ewis
    -0.20
    preci
    -0.20
    ']=="
    -0.19
    æĭīå¼Ģ
    -0.19
     (*((
    -0.18
    POSITIVE LOGITS
    bben
    0.24
    isbury
    0.21
    çĮİ
    0.20
    emetery
    0.20
     Wrest
    0.20
    struments
    0.19
    OLVE
    0.19
    ornment
    0.19
    suming
    0.19
    æĺŁå·´
    0.19
    Activations Density 0.000%

    No Known Activations