© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 90329
    Prev
    Next
    INDEX
    Explanations

    conjunctions indicating contrast or continuation

    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
     neglected
    -0.09
    ayers
    -0.09
    apon
    -0.09
     Unfortunately
    -0.08
    unto
    -0.08
     nowhere
    -0.08
     Nun
    -0.08
    ayer
    -0.07
    ari
    -0.07
     especially
    -0.07
    POSITIVE LOGITS
     nonetheless
    0.49
     nevertheless
    0.48
    Nevertheless
    0.37
     Nonetheless
    0.35
     Nevertheless
    0.35
     however
    0.35
    however
    0.32
    However
    0.31
     HOWEVER
    0.29
     However
    0.29
    Activations Density 0.233%

    No Known Activations