© 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. 15930
    Prev
    Next
    INDEX
    Explanations

    ultimate control

    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
     unfortunately
    -0.11
     normalize
    -0.11
     modest
    -0.10
     naturally
    -0.10
     Official
    -0.10
     normalized
    -0.10
     disag
    -0.09
     geld
    -0.09
     official
    -0.09
     dess
    -0.09
    POSITIVE LOGITS
     paradox
    0.17
     ultimately
    0.17
     underlying
    0.14
     Ultimately
    0.13
     voluntarily
    0.13
    Ultimately
    0.13
     beforehand
    0.12
     carefully
    0.12
     relinqu
    0.12
     secretly
    0.12
    Activations Density 0.030%

    No Known Activations