© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen2.5-7B-IT
    5. 20-MATRYOSHKA-65K
    7. 840
    Prev
    Next
    INDEX
    Explanations

    usual or standard

    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
    CLUDED
    -0.28
    uxtap
    -0.26
    个人è§ĤçĤ¹
    -0.24
    é¢ĺ主
    -0.24
    ungeons
    -0.23
     boobs
    -0.23
    åı¯ä»¥æĽ´å¥½
    -0.22
    ä½ľåĵģåĨħ容
    -0.22
    ä»İæĿ¥æ²¡
    -0.21
    åħ·ä½ĵåĨħ容
    -0.21
    POSITIVE LOGITS
    åģļæ³ķ
    0.31
    /common
    0.26
    /default
    0.25
    cy
    0.24
    çļĦåģļæ³ķ
    0.23
    (normal
    0.23
    fare
    0.23
    å¥Ĺè·¯
    0.23
     normal
    0.23
    assed
    0.23
    Activations Density 2.721%

    No Known Activations