© 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. 431
    Prev
    Next
    INDEX
    Explanations

    identifiers followed by variations

    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
    2
    -0.16
    3
    -0.16
    8
    -0.16
    1
    -0.15
    4
    -0.15
    7
    -0.14
    6
    -0.14
    9
    -0.13
    5
    -0.13
    0
    -0.10
    POSITIVE LOGITS
    âĢ³
    0.29
    âĢ²
    0.24
    swith
    0.14
    0.13
    toa
    0.13
    ï¸ı
    0.13
    -transitional
    0.12
    .amazonaws
    0.12
    uida
    0.12
    pga
    0.12
    Activations Density 1.361%

    No Known Activations