© 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. 63
    Prev
    Next
    INDEX
    Explanations

    should

    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
    ä½łéľĢè¦ģ
    -0.21
     calloc
    -0.20
    stanbul
    -0.19
     need
    -0.19
    éľĢè¦ģçĶ¨
    -0.19
    ESCO
    -0.18
    ÙĥÙĪر
    -0.18
    æĦ¿æĦı
    -0.18
    è¦ģç´§
    -0.18
    纽带
    -0.18
    POSITIVE LOGITS
     be
    0.29
    ering
    0.25
    clide
    0.24
    elight
    0.23
    :CGRect
    0.23
    ksam
    0.23
    ered
    0.23
    nt
    0.23
    ropri
    0.23
    èĢĥèĻij
    0.23
    Activations Density 1.121%

    No Known Activations