© 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. 58305
    Prev
    Next
    INDEX
    Explanations

    concatenate

    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
    hash
    -0.09
    ialis
    -0.09
    alling
    -0.09
    iele
    -0.09
    ler
    -0.08
     multis
    -0.08
    ially
    -0.08
    led
    -0.08
    pt
    -0.08
    ialized
    -0.08
    POSITIVE LOGITS
    enate
    0.11
    ening
    0.11
    ened
    0.10
     Primer
    0.10
    enaries
    0.10
    en
    0.10
    EN
    0.10
    ention
    0.09
    ene
    0.08
    cce
    0.08
    Activations Density 0.003%

    No Known Activations