© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen2.5-7B-IT
    5. 20-MATRYOSHKA-CHAT-65K
    7. 46980
    Prev
    Next
    INDEX
    Explanations

    ")"

    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
    Negative Logits
    ¡´
    -0.29
    strconv
    -0.28
     fkk
    -0.27
    ä¸ī大èģĮä¸ļ
    -0.27
    ĵĺ
    -0.27
     addCriterion
    -0.26
     ÑģеÑĢÑĮезн
    -0.25
    istring
    -0.25
    ")));
    -0.25
    ±ħ
    -0.25
    POSITIVE LOGITS
    addtogroup
    0.26
    ç´¢
    0.21
    han
    0.20
     اÙĦÙħشترÙĥ
    0.20
     overhead
    0.20
    çĭ¬
    0.19
    er
    0.19
    ÙĪضÙĪع
    0.19
    ahn
    0.19
     inclus
    0.19
    Activations Density 0.002%

    No Known Activations