© 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. 88890
    Prev
    Next
    INDEX
    Explanations

    companion and accompanying 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
    uft
    -0.09
    rz
    -0.09
     dere
    -0.09
     dumb
    -0.08
    endor
    -0.08
    busters
    -0.08
     preload
    -0.08
     vivid
    -0.08
    URAL
    -0.08
     garage
    -0.08
    POSITIVE LOGITS
     companion
    0.23
     Companion
    0.23
     companions
    0.22
     accompany
    0.16
     accompanying
    0.16
     camar
    0.16
    compan
    0.15
     accom
    0.15
     accompanied
    0.14
     accompanies
    0.14
    Activations Density 0.012%

    No Known Activations