© 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. 5865
    Prev
    Next
    INDEX
    Explanations

    incidental or accidental events

    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
     mq
    -0.10
     OMIT
    -0.09
     expend
    -0.09
     wasting
    -0.08
    .opens
    -0.08
    ymb
    -0.08
     legion
    -0.08
     soph
    -0.08
     prive
    -0.08
     stranger
    -0.08
    POSITIVE LOGITS
     necessary
    0.21
     accidentally
    0.20
     inadvertently
    0.19
     preparing
    0.19
     ostensibly
    0.18
     needed
    0.18
     accidental
    0.17
     Necessary
    0.17
     incidental
    0.17
     prepar
    0.17
    Activations Density 1.236%

    No Known Activations