© 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. 32547
    Prev
    Next
    INDEX
    Explanations

    way to alternatives

    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
     attempt
    -0.10
     because
    -0.10
    Meg
    -0.10
    olk
    -0.10
    ora
    -0.09
    usu
    -0.09
    because
    -0.09
     differently
    -0.09
    azu
    -0.09
     herself
    -0.09
    POSITIVE LOGITS
     ways
    0.16
     alternatives
    0.14
     substitutes
    0.11
     way
    0.10
     alternative
    0.10
     Alternative
    0.10
     preferable
    0.10
     better
    0.09
     dic
    0.09
     places
    0.09
    Activations Density 0.071%

    No Known Activations