© 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. 1258
    Prev
    Next
    INDEX
    Explanations

    note/notice

    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
     }};↵
    -0.21
    iram
    -0.20
     airstrikes
    -0.20
    -prepend
    -0.20
    cen
    -0.19
    ãİŀ
    -0.19
    	glm
    -0.19
    ṡ
    -0.19
    aret
    -0.19
     DialogInterface
    -0.19
    POSITIVE LOGITS
     note
    0.32
     Note
    0.28
     notice
    0.27
    --;↵↵
    0.25
    è¦ģ注æĦı
    0.25
    注æĦıåĪ°
    0.24
     Noticed
    0.23
     since
    0.22
     following
    0.22
    Note
    0.22
    Activations Density 0.586%

    No Known Activations