© 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. 46619
    Prev
    Next
    INDEX
    Explanations

    mixed fragments

    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
    æŁ¥çľĭ详æĥħ
    -0.26
    '+↵
    -0.23
    *******************************************************************************/↵
    -0.22
    uhe
    -0.22
    },'
    -0.22
    .PropTypes
    -0.21
    **/↵↵
    -0.21
    .kode
    -0.21
    handleRequest
    -0.21
    UGC
    -0.21
    POSITIVE LOGITS
    coholic
    0.21
    åĩºèĩª
    0.20
     Ember
    0.18
    ÙĤتر
    0.18
    ansom
    0.18
    è§ĨåIJ¬èĬĤ缮
    0.18
     dudes
    0.18
    asmine
    0.17
     openFileDialog
    0.17
    oop
    0.17
    Activations Density 0.001%

    No Known Activations