© 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-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 29711
    Prev
    Next
    INDEX
    Explanations

    Ro, RO, ro

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    bcywinski/Olmo-3-32B-Base-SAE/saes_allenai_Olmo-3-1125-32B_batch_top_k/resid_post_layer_32
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     inde
    -0.12
    erve
    -0.10
    agina
    -0.10
    argent
    -0.10
    ucer
    -0.09
    PLIC
    -0.09
     dis
    -0.09
    cura
    -0.09
     ind
    -0.09
     doubly
    -0.09
    POSITIVE LOGITS
     ro
    0.15
    -ro
    0.13
    Ro
    0.12
    (ro
    0.12
     Ro
    0.12
     roster
    0.11
    inton
    0.11
     Roh
    0.11
     roast
    0.11
     roaming
    0.11
    Activations Density 0.016%

    No Known Activations