© 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. 88279
    Prev
    Next
    INDEX
    Explanations

    one person accompanying another

    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
    hes
    -0.09
    linik
    -0.09
     pneum
    -0.09
     Automatic
    -0.08
     hut
    -0.08
     collective
    -0.08
     automatic
    -0.08
     begging
    -0.08
     Collective
    -0.08
     discovers
    -0.08
    POSITIVE LOGITS
     companions
    0.27
     companion
    0.21
     accompany
    0.20
     Companion
    0.20
    compan
    0.17
     accompanying
    0.17
     mentor
    0.17
     assistance
    0.16
     escorts
    0.16
     escort
    0.16
    Activations Density 0.021%

    No Known Activations