© 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. 6273
    Prev
    Next
    INDEX
    Explanations

    opportunity

    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
    117
    -0.09
     handful
    -0.09
     numerous
    -0.09
     harm
    -0.08
    sburg
    -0.08
     dozens
    -0.08
     damage
    -0.07
     Numerous
    -0.07
    617
    -0.07
    hti
    -0.07
    POSITIVE LOGITS
     same
    0.22
     utmost
    0.21
     beginnings
    0.18
    same
    0.17
     equivalent
    0.17
     SAME
    0.16
     slightest
    0.16
     illusion
    0.15
     possibility
    0.15
     ability
    0.14
    Activations Density 0.686%

    No Known Activations