© 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. 1232
    Prev
    Next
    INDEX
    Explanations

    minimum

    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
    edly
    -0.09
    dyn
    -0.09
    ility
    -0.09
    adin
    -0.09
    ingleton
    -0.08
    imestamp
    -0.08
    dess
    -0.08
    NESS
    -0.08
     immedi
    -0.08
    eking
    -0.08
    POSITIVE LOGITS
    /max
    0.17
    IMUM
    0.15
    ималÑĮ
    0.14
     veniam
    0.14
    utely
    0.13
    imize
    0.13
    erals
    0.13
    usc
    0.12
    imized
    0.12
    ogy
    0.11
    Activations Density 0.473%

    No Known Activations