© 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. 46400
    Prev
    Next
    INDEX
    Explanations

    technical data or code

    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
    /Branch
    -0.29
    @student
    -0.26
    );$
    -0.24
    婳
    -0.24
    /Dk
    -0.24
    )new
    -0.23
    /Foundation
    -0.23
    EFR
    -0.23
    æ·ı
    -0.23
     */↵↵↵↵
    -0.23
    POSITIVE LOGITS
     hairst
    0.23
     ejected
    0.22
    åıĭ们
    0.19
    dot
    0.19
     pione
    0.19
     ypos
    0.19
    æķ£
    0.19
     Crushers
    0.19
     cage
    0.18
    /off
    0.18
    Activations Density 0.002%

    No Known Activations