© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1025-7B
    5. 16-RES-MATRYOSHKA-65K
    7. 3605
    Prev
    Next
    INDEX
    Explanations

    available or reserved capacity

    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
    erek
    -0.08
     Reach
    -0.08
    .cum
    -0.08
    Hdr
    -0.08
    edor
    -0.08
    ackages
    -0.08
    kir
    -0.08
     маÑĤ
    -0.08
     sph
    -0.08
     Ole
    -0.08
    POSITIVE LOGITS
     dedicated
    0.15
     reserved
    0.14
     dedic
    0.13
     spare
    0.13
     unused
    0.13
     available
    0.13
     resources
    0.13
     devoted
    0.13
     dedicate
    0.12
     Available
    0.12
    Activations Density 0.367%

    No Known Activations