© 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
    3. Olmo-3-1025-7B
    5. 16-RES-MATRYOSHKA-65K
    7. 1593
    Prev
    Next
    INDEX
    Explanations

    fill this, wondered if, most of, find numerous, receiving increased, prove lethal, proven to, proved equally, gained considerable, play a

    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
     misunder
    -0.13
    	throws
    -0.12
    ãģĵãĤĵ
    -0.12
    	↵	↵↵
    -0.12
    	↵	↵	↵	↵
    -0.12
    	Copyright
    -0.12
    orang
    -0.11
    	internal
    -0.11
    	TEST
    -0.11
    ãģŁãģł
    -0.11
    POSITIVE LOGITS
    0.13
    <|fim_middle|>
    0.13
    <|fim_suffix|>
    0.12
    ÂŃ
    0.09
    el
    0.09
    //
    0.08
    ï
    0.08
    (!
    0.08
    acent
    0.08
     ÂŃ
    0.07
    Activations Density 9.306%

    No Known Activations