© 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. 46205
    Prev
    Next
    INDEX
    Explanations

    code specification

    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
    ðŁĵIJ
    -0.23
    ebile
    -0.22
    âļĹ
    -0.22
    (iOS
    -0.21
    usterity
    -0.21
    UITextField
    -0.20
    antu
    -0.20
    ampoo
    -0.20
    iji
    -0.19
    zbollah
    -0.19
    POSITIVE LOGITS
     Proud
    0.20
    <link
    0.19
    è¿Ļæīįæĺ¯
    0.19
    ilestone
    0.19
    raud
    0.19
    æĤ´
    0.19
    olin
    0.19
    èĨĺ
    0.19
    statt
    0.18
    à¸łà¸²à¸§à¸°
    0.18
    Activations Density 0.004%

    No Known Activations