© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Olmo-3-1025-7B
    3. 16-RES-MATRYOSHKA-65K
    4. 1902
    Prev
    Next
    INDEX
    Explanations

    code or structured item introductions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    decoderesearch/olmo-3-saes/olmo-3-1025-7b
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    <|fim_suffix|>
    -0.11
     and
    -0.10
     of
    -0.08
    ,
    -0.08
    �t
    -0.07
     the
    -0.07
    	
    -0.07
    ÂŃ
    -0.06
     =
    -0.06
    .assertj
    -0.06
    POSITIVE LOGITS
    	Created
    0.21
    <main
    0.21
    />.↵
    0.20
    (PHP
    0.19
    <HTML
    0.19
    <select
    0.19
    (END
    0.19
     Interracial
    0.18
    -ln
    0.18
    (KEY
    0.18
    Activations Density 2.106%

    No Known Activations