© 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. 3674
    Prev
    Next
    INDEX
    Explanations

    quoted text starts sentences

    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
    .Then
    -0.09
    until
    -0.09
    931
    -0.08
    emouth
    -0.08
    omid
    -0.08
     eventually
    -0.07
    aye
    -0.07
     ultimately
    -0.07
    alous
    -0.07
     eventual
    -0.07
    POSITIVE LOGITS
    liv
    0.09
     Immediately
    0.09
    íĻ
    0.09
     });↵↵↵↵
    0.09
    arte
    0.09
    EEP
    0.08
     devastation
    0.08
    caption
    0.08
     immediately
    0.08
     signed
    0.08
    Activations Density 0.116%

    No Known Activations