© 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-65K
    7. 2908
    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/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
    娱ä¹IJåľº
    -0.28
    å°ıç¼ĸä¸Ģèµ·
    -0.23
     OnTrigger
    -0.23
    irie
    -0.22
     seznam
    -0.21
    _NONNULL
    -0.21
     perpetr
    -0.20
    æĢı
    -0.20
    :System
    -0.20
    -strokes
    -0.20
    POSITIVE LOGITS
    çĻĸ
    0.20
    èµį
    0.19
    NavController
    0.19
    éĢł
    0.19
    åºļ
    0.18
    -mouth
    0.18
    以为
    0.18
     strchr
    0.18
     Parliamentary
    0.18
    kelas
    0.18
    Activations Density 0.084%

    No Known Activations