© 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. 2507
    Prev
    Next
    INDEX
    Explanations

    events

    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
    avigate
    -0.21
    <Animator
    -0.20
    ilst
    -0.19
    olidays
    -0.19
    ollapse
    -0.19
    },č↵č↵
    -0.19
    avanaugh
    -0.19
    (_('
    -0.19
    apan
    -0.18
    erialization
    -0.18
    POSITIVE LOGITS
    çļĦä¸ĢåĪĩ
    0.27
     events
    0.27
    ä¸ĢåĪĩéĥ½
    0.26
    äºĭ件
    0.25
     Events
    0.24
    ëļ±
    0.24
    äºĭæĥħ
    0.24
    æ·ı
    0.24
    åıijçĶŁçļĦ
    0.23
     happen
    0.23
    Activations Density 0.737%

    No Known Activations