© 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. 28135
    Prev
    Next
    INDEX
    Explanations

    ubiquitous, everywhere, pervasive

    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
    stime
    -0.10
     Ferr
    -0.10
     indebted
    -0.09
    trad
    -0.09
    ifo
    -0.08
     reserved
    -0.08
    biz
    -0.08
     miesz
    -0.08
    stag
    -0.08
     Lind
    -0.08
    POSITIVE LOGITS
     everywhere
    0.73
     Everywhere
    0.65
     ubiquitous
    0.41
     EVERY
    0.38
     omnip
    0.37
     wherever
    0.36
     pervasive
    0.35
     ubiqu
    0.35
     perv
    0.33
     anywhere
    0.32
    Activations Density 0.623%

    No Known Activations