© 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. 7592
    Prev
    Next
    INDEX
    Explanations

    ongoing or recurring conditions

    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
     unequiv
    -0.09
     strictly
    -0.09
    -solid
    -0.08
     directly
    -0.08
     Alexandra
    -0.08
    _hard
    -0.08
    het
    -0.08
     Spotlight
    -0.08
     unmistak
    -0.07
     Independ
    -0.07
    POSITIVE LOGITS
     ongoing
    0.36
     recurring
    0.29
     repeated
    0.27
    ongo
    0.26
     continuous
    0.25
     repetitive
    0.23
     continual
    0.23
     recurrent
    0.22
     repeatedly
    0.22
     sustained
    0.22
    Activations Density 0.352%

    No Known Activations