© 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. 1371
    Prev
    Next
    INDEX
    Explanations

    of the

    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
    limits
    -0.10
    =DB
    -0.09
    extras
    -0.09
    nett
    -0.09
     nothing
    -0.09
    enas
    -0.09
    Bean
    -0.09
     airs
    -0.09
    ikhail
    -0.09
    indle
    -0.09
    POSITIVE LOGITS
     each
    0.23
     EACH
    0.15
    each
    0.15
     Each
    0.14
    Each
    0.12
     individual
    0.11
     every
    0.10
    æ¯ı
    0.10
     chaque
    0.10
     these
    0.10
    Activations Density 2.364%

    No Known Activations