© 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. 4
    Prev
    Next
    INDEX
    Explanations

    slashes

    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
     @{$
    -0.26
    åıªæĺ¯ä¸ºäºĨ
    -0.23
    cassert
    -0.22
    ("<?
    -0.21
    ,[],
    -0.20
    .argv
    -0.19
    éŃ
    -0.19
    è¸ŀ
    -0.19
    çĺ¸
    -0.19
    },'
    -0.19
    POSITIVE LOGITS
    razil
    0.21
    å¥ģ
    0.20
    mdb
    0.20
    PerPixel
    0.20
    itution
    0.19
    usra
    0.19
     Dans
    0.18
    posables
    0.18
    并
    0.18
    keterangan
    0.18
    Activations Density 0.112%

    No Known Activations