© 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. 32278
    Prev
    Next
    INDEX
    Explanations

    at best and at most

    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
     invariably
    -0.12
    lij
    -0.11
     omin
    -0.11
     nearer
    -0.10
     virtually
    -0.10
    (APP
    -0.10
     eer
    -0.10
     quite
    -0.10
     Farms
    -0.10
     unmistak
    -0.10
    POSITIVE LOGITS
     mildly
    0.11
    hope
    0.10
     luk
    0.10
     maybe
    0.10
     hope
    0.10
     occasionally
    0.09
    maybe
    0.09
     manslaughter
    0.09
     misguided
    0.09
     Noble
    0.09
    Activations Density 0.078%

    No Known Activations