© 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. 2650
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions

    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
    :selected
    -0.23
    ummings
    -0.22
    åľ¬
    -0.21
    +len
    -0.20
    xampp
    -0.20
    eur
    -0.19
    errated
    -0.19
    etal
    -0.18
    .TextUtils
    -0.18
    ;set
    -0.18
    POSITIVE LOGITS
    âĩĶ
    0.23
    æĢ¥æĢ§
    0.20
     (;;)
    0.20
    室åıĭ
    0.20
    ฿
    0.20
    çķļ
    0.19
    ogenerated
    0.19
    ihanna
    0.19
    SizePolicy
    0.19
     (;;
    0.18
    Activations Density 0.016%

    No Known Activations