© 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. 1474
    Prev
    Next
    INDEX
    Explanations

    NULL pointer

    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
    /Dk
    -0.27
    ÑģÑħод
    -0.22
    æݧèĤ¡éĽĨåĽ¢
    -0.21
    icensing
    -0.21
     IconData
    -0.20
    å¿¡
    -0.20
    åĮħåĮħ
    -0.20
    个çĻ¾åĪĨ
    -0.19
    é£İåIJ¹
    -0.18
    ä¸ĩæĪ·
    -0.18
    POSITIVE LOGITS
    alyzed
    0.31
    NULL
    0.29
     NULL
    0.28
    null
    0.25
    =NULL
    0.23
     null
    0.23
    	NULL
    0.23
    nullptr
    0.22
     ragaz
    0.22
    .NULL
    0.22
    Activations Density 1.263%

    No Known Activations