© 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. 14727
    Prev
    Next
    INDEX
    Explanations

    Names ending in -erd, -art, -ard

    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
    allee
    -0.10
     dri
    -0.09
    richt
    -0.09
     Kurd
    -0.09
    alte
    -0.09
    jid
    -0.08
     foresee
    -0.08
    OOT
    -0.08
    bras
    -0.08
    .shortcuts
    -0.08
    POSITIVE LOGITS
    shire
    0.10
    warm
    0.08
    .gdx
    0.08
    pcf
    0.08
    abeth
    0.08
    stadt
    0.07
     sog
    0.07
     invariant
    0.07
     azi
    0.07
     gost
    0.07
    Activations Density 0.109%

    No Known Activations