© 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. 8513
    Prev
    Next
    INDEX
    Explanations

    previous / past

    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
    atura
    -0.09
    Remaining
    -0.08
    /man
    -0.08
     Printable
    -0.08
    abouts
    -0.08
     Dio
    -0.08
     Nom
    -0.08
    sus
    -0.08
     sext
    -0.08
    veal
    -0.08
    POSITIVE LOGITS
     previous
    0.30
     Previous
    0.27
    previous
    0.24
    Previous
    0.23
     past
    0.22
     precedent
    0.22
     existing
    0.21
     Existing
    0.20
     history
    0.20
    _previous
    0.19
    Activations Density 0.491%

    No Known Activations