© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 33901
    Prev
    Next
    INDEX
    Explanations

    cleanup and recovery

    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
    æ£
    -0.11
    UNC
    -0.11
     rides
    -0.10
    otope
    -0.10
     sic
    -0.09
     sale
    -0.09
     Scratch
    -0.09
    .watch
    -0.09
    ROTO
    -0.09
    ichen
    -0.09
    POSITIVE LOGITS
     recovery
    0.13
     retrieving
    0.12
     collecting
    0.12
     recovering
    0.12
     retrie
    0.12
     restoration
    0.12
     gather
    0.12
    _recovery
    0.12
     gathering
    0.12
     Recovery
    0.11
    Activations Density 0.030%

    No Known Activations