© 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. 8225
    Prev
    Next
    INDEX
    Explanations

    storing or managing items

    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
    Negative Logits
     McCartney
    -0.10
    upd
    -0.09
     consciously
    -0.09
    noch
    -0.09
    chers
    -0.09
     Thor
    -0.09
    fout
    -0.09
     inhabited
    -0.09
    çķª
    -0.09
    alin
    -0.08
    POSITIVE LOGITS
     safely
    0.14
     overflow
    0.13
     temporarily
    0.12
     securely
    0.12
     conveniently
    0.12
     growing
    0.10
     Overflow
    0.10
     displaced
    0.10
    overflow
    0.10
    Secure
    0.10
    Activations Density 0.538%

    No Known Activations