© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 32209
    Prev
    Next
    INDEX
    Explanations

    weekly frequency

    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
    (using
    -0.09
     embar
    -0.09
    eb
    -0.09
     makeshift
    -0.08
    /inc
    -0.08
    _PART
    -0.08
    oyer
    -0.08
    again
    -0.08
     inevitably
    -0.08
     decre
    -0.08
    POSITIVE LOGITS
     regularly
    0.15
     weekly
    0.14
     subscribers
    0.13
     subscribing
    0.12
     daily
    0.12
     frequent
    0.12
     promises
    0.12
     monthly
    0.12
    weekly
    0.12
     subscriber
    0.11
    Activations Density 0.002%

    No Known Activations