© 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. 112764
    Prev
    Next
    INDEX
    Explanations

    argue, argue, contend, claim

    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
     contemplating
    -0.12
     contemplated
    -0.11
     hesitate
    -0.10
     confirmation
    -0.10
     thankful
    -0.10
     confirmed
    -0.10
     realised
    -0.09
     realization
    -0.09
    zn
    -0.09
     confirms
    -0.09
    POSITIVE LOGITS
     arguing
    0.32
     argue
    0.32
     argues
    0.30
     argued
    0.30
     argument
    0.27
     contends
    0.27
     contend
    0.26
     claim
    0.24
     claiming
    0.22
     contention
    0.22
    Activations Density 0.701%

    No Known Activations