© 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. 17733
    Prev
    Next
    INDEX
    Explanations

    GNU General Public License version 2 as

    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
     Eff
    -0.10
     Emoji
    -0.10
    à¸ĩ
    -0.10
     eff
    -0.10
     Lit
    -0.10
     Keystone
    -0.10
     corridors
    -0.10
     hun
    -0.09
    umo
    -0.09
     surre
    -0.09
    POSITIVE LOGITS
     Nunes
    0.08
    /disc
    0.07
     Rim
    0.07
    -final
    0.07
     thereof
    0.07
     by
    0.07
     slaves
    0.07
    COMPLETE
    0.07
     subt
    0.07
     nied
    0.07
    Activations Density 0.016%

    No Known Activations