© 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. 7933
    Prev
    Next
    INDEX
    Explanations

    expand your / their / our

    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
    ined
    -0.10
     próximo
    -0.09
    /actions
    -0.09
    ncia
    -0.09
    /from
    -0.09
     proper
    -0.09
    tracts
    -0.09
    Sys
    -0.09
    æŃ£ç¡®
    -0.09
    iken
    -0.09
    POSITIVE LOGITS
     their
    0.18
    /change
    0.17
    /update
    0.16
     your
    0.15
     existing
    0.14
     our
    0.13
     the
    0.12
    /mod
    0.12
    /im
    0.12
     Existing
    0.11
    Activations Density 0.296%

    No Known Activations