© 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. 5420
    Prev
    Next
    INDEX
    Explanations

    positive or favorable

    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
     Cle
    -0.09
     Powerful
    -0.08
     Masters
    -0.08
     Vocal
    -0.08
    baum
    -0.08
     sto
    -0.08
     Talking
    -0.08
    apur
    -0.08
     boldly
    -0.08
     bold
    -0.08
    POSITIVE LOGITS
     positive
    0.46
     Positive
    0.40
    positive
    0.39
    Positive
    0.37
     negative
    0.36
     positively
    0.36
    -positive
    0.34
     positives
    0.31
     favorable
    0.31
    _positive
    0.30
    Activations Density 0.398%

    No Known Activations