© 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. 46480
    Prev
    Next
    INDEX
    Explanations

    extras or benefits

    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
     Enough
    -0.11
     enough
    -0.09
    ivol
    -0.09
    arent
    -0.09
    ened
    -0.08
    Enough
    -0.08
     ongoing
    -0.08
     underlying
    -0.08
     amor
    -0.08
    iation
    -0.07
    POSITIVE LOGITS
     benefit
    0.17
     advantage
    0.16
     extras
    0.16
     bonus
    0.16
     added
    0.15
     expense
    0.14
     bonuses
    0.14
     benefits
    0.13
     functionality
    0.13
     attraction
    0.13
    Activations Density 0.030%

    No Known Activations