© 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. 2568
    Prev
    Next
    INDEX
    Explanations

    quantity or size descriptors

    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
     aun
    -0.08
    aven
    -0.07
    lobals
    -0.06
     bog
    -0.06
    ants
    -0.06
    ottes
    -0.06
    ivals
    -0.06
    AEA
    -0.06
    itives
    -0.06
     postcode
    -0.06
    POSITIVE LOGITS
     remaining
    0.13
     ensuing
    0.12
     nature
    0.12
    oubted
    0.10
    icot
    0.10
    -strong
    0.10
    remaining
    0.10
     Nature
    0.10
     confines
    0.10
    nature
    0.10
    Activations Density 0.404%

    No Known Activations