© 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. 56
    Prev
    Next
    INDEX
    Explanations

    de followed by names or specific endings

    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
     de
    -0.10
    de
    -0.10
    dep
    -0.10
    rov
    -0.09
    dev
    -0.09
    _de
    -0.09
    Delegate
    -0.09
    wich
    -0.09
     depot
    -0.08
    uv
    -0.08
    POSITIVE LOGITS
     facto
    0.12
    URIComponent
    0.11
     novo
    0.11
    construct
    0.10
    (strict
    0.10
     la
    0.10
    eken
    0.10
     unf
    0.10
     Quincy
    0.10
    ósito
    0.09
    Activations Density 0.794%

    No Known Activations