© 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. 48423
    Prev
    Next
    INDEX
    Explanations

    negation words followed by 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
    Not in Any Lists

    No Comments

    Negative Logits
    acre
    -0.11
    dre
    -0.10
     Ferr
    -0.09
    bane
    -0.08
    217
    -0.08
    enta
    -0.08
    lea
    -0.08
    atan
    -0.08
    ucker
    -0.08
     Bak
    -0.08
    POSITIVE LOGITS
     expect
    0.10
    etal
    0.10
    Hom
    0.10
     Archie
    0.09
    OLA
    0.09
    cco
    0.09
     Biography
    0.09
    .expect
    0.09
     intention
    0.09
    Bi
    0.09
    Activations Density 0.007%

    No Known Activations