© 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. 115423
    Prev
    Next
    INDEX
    Explanations

    pronoun subject followed by verb

    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
     Wants
    -0.12
     newfound
    -0.11
     dreaded
    -0.11
     burden
    -0.10
     WANT
    -0.10
     likely
    -0.10
     unfamiliar
    -0.10
     Likely
    -0.09
    urge
    -0.09
     desire
    -0.09
    POSITIVE LOGITS
     reminds
    0.15
     somehow
    0.13
     remind
    0.13
     always
    0.13
     IMO
    0.12
    555
    0.11
     fasc
    0.11
     relaxing
    0.11
     reminded
    0.10
     sempre
    0.10
    Activations Density 0.121%

    No Known Activations