© 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. 1886
    Prev
    Next
    INDEX
    Explanations

    travel and activities

    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
    滥
    -0.25
    åĬĽè¿ĺæĺ¯
    -0.24
    对çħ§æ£ĢæŁ¥
    -0.24
    æ®ĥ
    -0.24
    .getLatitude
    -0.24
     actionTypes
    -0.24
    å«Įçĸij
    -0.23
    âŁ¹
    -0.23
    å¤įå·¥å¤į
    -0.22
    被æĬĵ
    -0.22
    POSITIVE LOGITS
    æĢ§ä»·
    0.35
    æľīæľŁå¾Ĵ
    0.32
    ä½ı宿
    0.28
    ',//
    0.27
    æĶ»çķ¥
    0.26
    讪
    0.26
    ]int
    0.25
    -scalable
    0.25
    :';↵
    0.25
    nqu
    0.25
    Activations Density 3.686%

    No Known Activations