© 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. 308
    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
    âĿĸ
    -0.23
    /Dk
    -0.23
    alborg
    -0.23
    )NULL
    -0.21
    缮
    -0.20
    âĸİ
    -0.20
     èĩªåĬ¨çĶŁæĪIJ
    -0.19
     Blick
    -0.19
    elib
    -0.18
    NavLink
    -0.18
    POSITIVE LOGITS
    intree
    0.21
    arResult
    0.20
    IDA
    0.20
    appropri
    0.19
    oooooooo
    0.19
    -addons
    0.19
    istinguish
    0.18
    åį¸
    0.18
     UEFA
    0.18
    viar
    0.17
    Activations Density 0.001%

    No Known Activations