© 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. 4449
    Prev
    Next
    INDEX
    Explanations

    modification followed by comma

    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
    /reg
    -0.10
    RIEND
    -0.10
    -reg
    -0.09
    ÃĹ↵↵
    -0.09
    ighton
    -0.09
    алÑĮ
    -0.09
     tink
    -0.09
     ration
    -0.09
    Ack
    -0.08
    mant
    -0.08
    POSITIVE LOGITS
    vac
    0.08
     residences
    0.08
    jam
    0.08
     escort
    0.07
    uras
    0.07
    ÑĤÑĥ
    0.07
     spons
    0.07
     skyline
    0.07
    ëĵ¤
    0.07
     gord
    0.07
    Activations Density 0.023%

    No Known Activations