© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 8325
    Prev
    Next
    INDEX
    Explanations

    get [starter/proper/flight]

    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
    Negative Logits
     wikipedia
    -0.12
     Shed
    -0.11
     hypoc
    -0.10
     Pornhub
    -0.10
     Wikipedia
    -0.10
    ikipedia
    -0.10
     shedding
    -0.09
     bü
    -0.09
    CORD
    -0.09
     Chin
    -0.09
    POSITIVE LOGITS
     reliably
    0.11
     safely
    0.11
    akin
    0.10
     unbiased
    0.10
     besides
    0.10
    gratis
    0.10
     legitimately
    0.10
    rama
    0.10
     unconventional
    0.10
     Valent
    0.10
    Activations Density 0.002%

    No Known Activations