© 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. 50272
    Prev
    Next
    INDEX
    Explanations

    number of days or years

    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
     auss
    -0.10
    quo
    -0.09
    Loop
    -0.09
    wise
    -0.09
     Spike
    -0.09
    anco
    -0.08
     Alley
    -0.08
    \',
    -0.08
     revers
    -0.08
    å¸
    -0.08
    POSITIVE LOGITS
     aver
    0.09
     lava
    0.09
     categor
    0.09
     Bien
    0.09
    	next
    0.09
    .vol
    0.09
     fruitful
    0.09
    ikes
    0.09
     Creation
    0.09
     volcan
    0.09
    Activations Density 0.001%

    No Known Activations