© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen2.5-7B-IT
    5. 20-MATRYOSHKA-CHAT-65K
    7. 46264
    Prev
    Next
    INDEX
    Explanations

    code or corrupted text

    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/lmsys/matryoshka/k-100
    Prompts (Dashboard)
    16,384 prompts, 192 tokens each
    Dataset (Dashboard)
    chanind/lmsys-chat-1m-qwen-2.5
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    讧
    -0.20
    éĴı
    -0.19
    *)((
    -0.19
    riday
    -0.19
    issions
    -0.18
    zych
    -0.18
    arse
    -0.18
    ustomed
    -0.17
    个çĻ¾åĪĨ
    -0.17
    å¾ģ
    -0.17
    POSITIVE LOGITS
    ):?>↵
    0.28
    OCUS
    0.24
    æĤ¨çļĦåŃ©åŃIJ
    0.22
    .TryParse
    0.22
    /comment
    0.21
    ummings
    0.20
     авг
    0.20
    nia
    0.20
    ribly
    0.20
     bindActionCreators
    0.20
    Activations Density 0.001%

    No Known Activations