© 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-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 27063
    Prev
    Next
    INDEX
    Explanations

    Ros names and related words

    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
    acre
    -0.10
    885
    -0.10
     ens
    -0.10
     freedom
    -0.09
     underst
    -0.09
     lighten
    -0.09
     Drawer
    -0.09
     confer
    -0.09
     Basement
    -0.09
     Cliff
    -0.09
    POSITIVE LOGITS
    /ros
    0.13
    enthal
    0.12
    ario
    0.11
    coe
    0.10
    etta
    0.10
    set
    0.10
    anna
    0.09
    elyn
    0.09
    endale
    0.09
     eros
    0.09
    Activations Density 0.055%

    No Known Activations