© 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. 30131
    Prev
    Next
    INDEX
    Explanations

    plausible or convincing claims

    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
     rarity
    -0.10
     nou
    -0.10
    rupt
    -0.09
     Cri
    -0.09
     Carol
    -0.09
     querying
    -0.09
     Infant
    -0.09
    uner
    -0.09
     Nou
    -0.09
     abstraction
    -0.08
    POSITIVE LOGITS
     convincing
    0.47
     plausible
    0.44
     convinc
    0.44
     believable
    0.42
     realistic
    0.30
     credible
    0.29
     persuasive
    0.29
     compelling
    0.29
     convince
    0.26
     belie
    0.25
    Activations Density 0.098%

    No Known Activations