© 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. 8052
    Prev
    Next
    INDEX
    Explanations

    un- prefixes

    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
    aware
    -0.12
    locked
    -0.12
    parsed
    -0.11
    pars
    -0.11
    picked
    -0.11
    seen
    -0.11
    initialized
    -0.11
    cased
    -0.11
    pit
    -0.11
    uzzi
    -0.11
    POSITIVE LOGITS
    /un
    0.25
    -un
    0.13
    -Un
    0.11
    orth
    0.10
    (Un
    0.09
    assuming
    0.09
     spr
    0.09
    tility
    0.08
    amb
    0.08
    crate
    0.08
    Activations Density 0.390%

    No Known Activations