© 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. 828
    Prev
    Next
    INDEX
    Explanations

    mathematics departments

    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
     hook
    -0.09
     bon
    -0.08
    ants
    -0.08
    eer
    -0.08
    aries
    -0.08
    tp
    -0.08
    hou
    -0.07
    ship
    -0.07
    'aff
    -0.07
    rier
    -0.07
    POSITIVE LOGITS
    ematic
    0.22
    ematics
    0.22
    emat
    0.19
    .BigDecimal
    0.16
    bb
    0.16
    letes
    0.15
    jax
    0.15
    cal
    0.14
    nas
    0.14
    ieu
    0.12
    Activations Density 0.367%

    No Known Activations