© 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. 46493
    Prev
    Next
    INDEX
    Explanations

    analyze data

    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
    å¹´ä¹ĭä¹ħ
    -0.21
    ãİľ
    -0.20
    峪
    -0.20
    çµ·
    -0.20
     aid
    -0.19
    _DER
    -0.18
    åĨħ容
    -0.18
    $I
    -0.18
    离ä¸įå¼Ģ
    -0.18
     incur
    -0.18
    POSITIVE LOGITS
    UGINS
    0.21
    VIOUS
    0.21
    entifier
    0.21
    StateException
    0.21
    overe
    0.20
    -vars
    0.20
    FromBody
    0.20
    /rand
    0.20
    noticed
    0.20
    .kode
    0.19
    Activations Density 0.059%

    No Known Activations