© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen2.5-7B-IT
    5. 20-MATRYOSHKA-65K
    7. 1457
    Prev
    Next
    INDEX
    Explanations

    specific names

    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/pile/matryoshka/k-100
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     misunder
    -0.28
     libertin
    -0.27
     arrang
    -0.26
    -toast
    -0.24
     fkk
    -0.24
     STDCALL
    -0.24
    éĽĨè£ħ
    -0.24
    _atual
    -0.24
    ä¸įåı¯æĪĸ
    -0.24
    'email
    -0.24
    POSITIVE LOGITS
    âĦł
    0.29
    æĸ°ä¸ŃåĽ½
    0.27
     Fortnite
    0.25
    å½ĵæŶçļĦ
    0.24
    å®ŀä¸ļ
    0.24
     telegram
    0.24
    èĭıèģĶ
    0.23
    裨
    0.23
     Telegram
    0.23
    alborg
    0.23
    Activations Density 6.179%

    No Known Activations