© 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. 585
    Prev
    Next
    INDEX
    Explanations

    word suffixes

    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
    #ga
    -0.47
    rippling
    -0.47
    /↵↵↵↵
    -0.44
    'icon
    -0.43
    #aa
    -0.43
    .nz
    -0.42
    icter
    -0.41
     Interracial
    -0.41
    rary
    -0.40
    :'.$
    -0.40
    POSITIVE LOGITS
    ing
    0.40
    ,
    0.38
    -
    0.37
    e
    0.37
    1
    0.36
     intimid
    0.36
    0.36
    0
    0.36
    :
    0.35
     (
    0.35
    Activations Density 15.543%

    No Known Activations