© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 31668
    Prev
    Next
    INDEX
    Explanations

    verb definitions or grammatical properties

    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
     Uns
    -0.09
     genus
    -0.08
    âĢ¦the
    -0.08
     Gloves
    -0.08
     bre
    -0.08
     socks
    -0.08
     booth
    -0.07
    ropp
    -0.07
     Ou
    -0.07
    eka
    -0.07
    POSITIVE LOGITS
     thrust
    0.11
     undermin
    0.11
     cleanse
    0.10
     Harden
    0.10
     hdc
    0.10
     Erect
    0.10
    tid
    0.10
     vacc
    0.10
    hus
    0.09
     Cleans
    0.09
    Activations Density 0.095%

    No Known Activations