© 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. 158
    Prev
    Next
    INDEX
    Explanations

    Paper references

    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
    âĦł
    -0.21
     :↵↵↵↵
    -0.21
    NavController
    -0.19
    _smart
    -0.19
    ÑĤÑģÑı
    -0.19
     Kemp
    -0.18
    åŃ£åIJİ
    -0.18
     {?>↵
    -0.18
    廨
    -0.18
     scarc
    -0.18
    POSITIVE LOGITS
     Article
    0.22
     pii
    0.20
    qli
    0.20
    nnen
    0.20
    yle
    0.20
     Paper
    0.20
    sthrough
    0.20
    pii
    0.19
    ulence
    0.19
    Tech
    0.19
    Activations Density 0.152%

    No Known Activations