© 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. 177
    Prev
    Next
    INDEX
    Explanations

    create a

    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
     tudo
    -0.11
     those
    -0.11
     Dabei
    -0.10
    lei
    -0.10
    ROP
    -0.10
     altri
    -0.10
     them
    -0.10
    енÑĭ
    -0.10
     tutto
    -0.10
     oltre
    -0.10
    POSITIVE LOGITS
     a
    0.40
     an
    0.37
    ä¸Ģ个
    0.32
     another
    0.24
    	a
    0.22
    a
    0.21
    —a
    0.17
    an
    0.17
     eine
    0.16
    >a
    0.16
    Activations Density 3.606%

    No Known Activations