© 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. 2358
    Prev
    Next
    INDEX
    Explanations

    section beginnings

    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
    0
    -0.22
    1
    -0.22
    -0.21
    管
    -0.20
     returnValue
    -0.20
    BoxLayout
    -0.19
    享
    -0.19
     dette
    -0.19
     concent
    -0.18
    3
    -0.18
    POSITIVE LOGITS
     èĩªåĬ¨çĶŁæĪIJ
    0.32
     èĭ¥è¦ģ
    0.29
    slaught
    0.29
    ceptar
    0.28
    æĿ¨æ¬¢
    0.26
    -Cs
    0.25
    "';
    0.25
    /Dk
    0.24
    )prepare
    0.24
     **)
    0.23
    Activations Density 0.002%

    No Known Activations