© 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. 91523
    Prev
    Next
    INDEX
    Explanations

    advertisement

    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
    ifer
    -0.09
     Biz
    -0.08
     Prest
    -0.08
     sund
    -0.07
    PILE
    -0.07
    -env
    -0.07
     Obs
    -0.07
    ves
    -0.07
     prest
    -0.07
     Sting
    -0.06
    POSITIVE LOGITS
     Advertisement
    0.21
     advertisement
    0.18
     advertisements
    0.18
    Advertisement
    0.17
     adverts
    0.16
     advertise
    0.16
     Ads
    0.16
     advert
    0.15
     advertis
    0.15
     Advertising
    0.14
    Activations Density 0.009%

    No Known Activations