© 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. 4043
    Prev
    Next
    INDEX
    Explanations

    Ca^2+ ^, O~2~, CO~2~, NO~2~, NO~3~

    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
    umer
    -0.10
    è¾
    -0.10
    že
    -0.10
    chez
    -0.10
    opot
    -0.10
    oes
    -0.10
    usher
    -0.09
    ocl
    -0.09
    ushi
    -0.09
     Wings
    -0.09
    POSITIVE LOGITS
    ASTER
    0.06
    sta
    0.06
    stadt
    0.06
    rix
    0.06
    asters
    0.06
    sv
    0.06
     activ
    0.06
    sey
    0.06
    chr
    0.05
     lst
    0.05
    Activations Density 0.055%

    No Known Activations