© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1025-7B
    5. 16-RES-MATRYOSHKA-65K
    7. 2764
    Prev
    Next
    INDEX
    Explanations

    sites

    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
    instead
    -0.11
    etz
    -0.10
    ipo
    -0.09
    pan
    -0.09
     BUILD
    -0.09
    arde
    -0.09
     instead
    -0.09
    lement
    -0.09
     Build
    -0.09
    headline
    -0.09
    POSITIVE LOGITS
     naturally
    0.13
     automatically
    0.12
     indirectly
    0.10
     anyhow
    0.09
    ucha
    0.09
    GEST
    0.08
    Automatic
    0.08
     Automatically
    0.08
     temporarily
    0.08
    -default
    0.08
    Activations Density 0.418%

    No Known Activations