© 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. 2170
    Prev
    Next
    INDEX
    Explanations

    say "number"

    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
    Unavailable
    -0.22
    ↵↵
    -0.20
    æĶ¿åħļ
    -0.19
     ult
    -0.19
    #ad
    -0.18
    [MAXN
    -0.18
    chte
    -0.18
    \Template
    -0.18
     Infos
    -0.17
    forgettable
    -0.17
    POSITIVE LOGITS
     Melania
    0.21
     ksi
    0.21
    -Cs
    0.21
    ãĢĤwww
    0.21
    âĵĩ
    0.21
    reeNode
    0.21
    steder
    0.21
    ToF
    0.20
    _UD
    0.20
    whelming
    0.19
    Activations Density 0.134%

    No Known Activations