© 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. 112774
    Prev
    Next
    INDEX
    Explanations

    verbs followed by prepositions

    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
     nearby
    -0.12
    erman
    -0.11
    arde
    -0.11
    ateg
    -0.11
    upa
    -0.11
    wig
    -0.10
     Nearby
    -0.10
     insistence
    -0.10
     Charm
    -0.10
    adera
    -0.10
    POSITIVE LOGITS
     receives
    0.21
     receive
    0.19
     receiving
    0.19
     witness
    0.16
     Receive
    0.16
     encountering
    0.16
     witnessing
    0.16
     invol
    0.16
    receive
    0.16
     encounter
    0.15
    Activations Density 0.278%

    No Known Activations