© 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. 18567
    Prev
    Next
    INDEX
    Explanations

    easy to use verbs

    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
     apro
    -0.09
    оÑı
    -0.09
     kron
    -0.08
    acted
    -0.08
     sque
    -0.08
     shield
    -0.08
     Prest
    -0.08
    /address
    -0.08
     dazz
    -0.08
     Kov
    -0.08
    POSITIVE LOGITS
     voluntary
    0.10
    omas
    0.09
    itto
    0.09
     Falk
    0.09
    unders
    0.09
    InstanceOf
    0.09
     Princip
    0.09
     upsetting
    0.09
    CAF
    0.09
     bois
    0.09
    Activations Density 0.003%

    No Known Activations