© 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. 45873
    Prev
    Next
    INDEX
    Explanations

    diverse languages and topics

    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
    chsel
    -0.22
    aber
    -0.20
    proof
    -0.19
    ewise
    -0.19
    åįł
    -0.18
    ëļĿ
    -0.18
     humili
    -0.18
    æ¯Ķäºļ
    -0.17
     deduct
    -0.17
    HideInInspector
    -0.17
    POSITIVE LOGITS
    'email
    0.21
    ÑģÑĤолÑĮ
    0.21
    'icon
    0.20
    åĵŃäºĨ
    0.20
    .squeeze
    0.20
    nze
    0.20
    ramework
    0.19
    DRV
    0.19
    &type
    0.19
    ниÑİ
    0.19
    Activations Density 0.001%

    No Known Activations