© 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. 46539
    Prev
    Next
    INDEX
    Explanations

    numbers and values

    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
     earthqu
    -0.23
    é¾ĥ
    -0.23
    éĩįè¦ģåİŁåĽł
    -0.23
    åĽ½éĻħåľ¨çº¿
    -0.22
    redicate
    -0.22
    elpers
    -0.21
    -Cs
    -0.21
    =Value
    -0.21
    odesk
    -0.20
    婳
    -0.20
    POSITIVE LOGITS
     dolayı
    0.20
    fore
    0.19
    .centerX
    0.19
    ÙħشاÙĩ
    0.19
     ttl
    0.19
    ç®Ĺ
    0.18
    çĶŁç´ł
    0.18
    æį¢
    0.18
    äºĶè¡Į
    0.18
    çĵ¤
    0.17
    Activations Density 0.017%

    No Known Activations