© 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. 2396
    Prev
    Next
    INDEX
    Explanations

    people's

    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
     else
    -0.12
    (es
    -0.12
     who
    -0.11
    ’
    -0.11
    da
    -0.10
     whom
    -0.09
    og
    -0.09
    else
    -0.09
    ou
    -0.09
     dess
    -0.09
    POSITIVE LOGITS
    hood
    0.10
    's
    0.09
    unic
    0.09
    iem
    0.09
     pleasing
    0.08
    scape
    0.08
    usb
    0.08
    idos
    0.08
    WISE
    0.08
    aire
    0.08
    Activations Density 0.103%

    No Known Activations