© 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. 57808
    Prev
    Next
    INDEX
    Explanations

    micro- prefixes

    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
    ceph
    -0.10
    aggregate
    -0.10
     Pants
    -0.10
    /mac
    -0.09
     Pieces
    -0.09
    ippo
    -0.09
    NAL
    -0.09
    angkan
    -0.09
     Corey
    -0.09
    ienen
    -0.09
    POSITIVE LOGITS
    ré
    0.08
    ina
    0.08
    unk
    0.08
    cie
    0.07
    ively
    0.07
    rad
    0.07
    =<
    0.07
    ham
    0.07
    chest
    0.07
    rea
    0.07
    Activations Density 0.124%

    No Known Activations