© 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. 46279
    Prev
    Next
    INDEX
    Explanations

    Come

    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
    jec
    -0.22
     ÅŁeh
    -0.20
    getParam
    -0.20
    è¤ĵ
    -0.20
    lashes
    -0.19
    abama
    -0.19
     (!((
    -0.19
    /Dk
    -0.19
    ".↵↵↵↵
    -0.19
    ottenham
    -0.19
    POSITIVE LOGITS
    Nhap
    0.21
    vertiser
    0.21
    æĨĶ
    0.21
    sprintf
    0.20
    âĪ¬
    0.19
    被æ·ĺæ±°
    0.19
    âĪĬ
    0.19
    éħIJ
    0.19
    :CGRect
    0.18
     Klopp
    0.18
    Activations Density 0.009%

    No Known Activations