© 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. 28598
    Prev
    Next
    INDEX
    Explanations

    moments and memories

    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
    osto
    -0.11
     Budd
    -0.11
     Pall
    -0.10
     ROOT
    -0.10
     healed
    -0.10
    atab
    -0.10
    .codes
    -0.10
    ukan
    -0.09
     intrigue
    -0.09
    231
    -0.09
    POSITIVE LOGITS
     moments
    0.23
     forever
    0.22
     Moments
    0.21
     moment
    0.20
     Forever
    0.19
     Moment
    0.19
     preserve
    0.17
     memor
    0.17
     everlasting
    0.16
    Moment
    0.16
    Activations Density 0.045%

    No Known Activations