© 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. 33850
    Prev
    Next
    INDEX
    Explanations

    bombarded, ubiquitous, everywhere

    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
    ief
    -0.10
     Invent
    -0.10
     manually
    -0.10
    /ar
    -0.10
     Gavin
    -0.10
     inventor
    -0.10
     invent
    -0.10
     handbook
    -0.10
     Webcam
    -0.09
     improvised
    -0.09
    POSITIVE LOGITS
     everywhere
    0.28
     media
    0.26
     Everywhere
    0.26
     ubiquitous
    0.24
     pervasive
    0.24
     bombard
    0.23
     omnip
    0.22
     inund
    0.22
     saturated
    0.21
     satur
    0.21
    Activations Density 0.299%

    No Known Activations