© 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. 54479
    Prev
    Next
    INDEX
    Explanations

    math operators * plus minus

    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
    èĩ³
    -0.09
    ioned
    -0.09
    #{
    -0.09
    ¶
    -0.08
    gon
    -0.08
     iter
    -0.08
     appoint
    -0.08
     prospect
    -0.08
    ạo
    -0.08
    seq
    -0.08
    POSITIVE LOGITS
    nar
    0.08
     arrangement
    0.08
     bang
    0.08
    ruk
    0.08
    opol
    0.08
     multiplication
    0.08
     neh
    0.08
     arrang
    0.07
     det
    0.07
    obo
    0.07
    Activations Density 0.006%

    No Known Activations