© 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. 25993
    Prev
    Next
    INDEX
    Explanations

    names ending in 'ah', 'ia', 'o', 'i', 'a'

    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
    utes
    -0.08
     watering
    -0.08
     wardrobe
    -0.08
    pel
    -0.08
     disemb
    -0.08
    ientos
    -0.08
     Bart
    -0.08
     eligible
    -0.08
    974
    -0.08
    .decorators
    -0.08
    POSITIVE LOGITS
    bose
    0.09
     subt
    0.09
     flute
    0.09
    )::
    0.09
    inia
    0.09
     hitch
    0.09
     nad
    0.09
    Ŀ
    0.09
     boyc
    0.08
    VRT
    0.08
    Activations Density 0.082%

    No Known Activations