© 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. 32614
    Prev
    Next
    INDEX
    Explanations

    negation 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
     deliberate
    -0.11
    geist
    -0.10
     intentional
    -0.10
     deliberately
    -0.10
     conscious
    -0.09
     intentionally
    -0.09
     unavoid
    -0.09
    athering
    -0.09
     consciously
    -0.09
    zem
    -0.09
    POSITIVE LOGITS
     elabor
    0.13
     otherwise
    0.12
     disgu
    0.11
     haste
    0.11
     urg
    0.10
     further
    0.10
     directly
    0.10
     embell
    0.10
    elf
    0.09
    -qu
    0.09
    Activations Density 0.024%

    No Known Activations