© 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. 115934
    Prev
    Next
    INDEX
    Explanations

    usual [noun]

    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
    onds
    -0.11
     ideally
    -0.10
    avor
    -0.09
    isma
    -0.09
    oose
    -0.09
     specifically
    -0.09
     collectively
    -0.09
    aryl
    -0.08
    lah
    -0.08
    esh
    -0.08
    POSITIVE LOGITS
     fare
    0.22
     suspects
    0.21
     usual
    0.14
     disclaimer
    0.12
     ubiquitous
    0.12
     expected
    0.11
     nowadays
    0.11
    fare
    0.11
     fares
    0.10
     spiel
    0.10
    Activations Density 0.239%

    No Known Activations