© 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. 4500
    Prev
    Next
    INDEX
    Explanations

    First mention of names or specific terms

    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
    abus
    -0.10
    unya
    -0.09
    eti
    -0.09
    289
    -0.09
     foil
    -0.09
     EOF
    -0.09
     Collapse
    -0.08
    avan
    -0.08
    UED
    -0.08
    iao
    -0.08
    POSITIVE LOGITS
     first
    0.12
     Firstly
    0.09
    First
    0.09
     examination
    0.09
     Aqu
    0.08
     commonly
    0.08
    ikal
    0.08
     ideally
    0.08
     standard
    0.08
     First
    0.08
    Activations Density 0.009%

    No Known Activations