© 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. 48841
    Prev
    Next
    INDEX
    Explanations

    nor, but, since, unless

    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
     due
    -0.13
    oger
    -0.12
     Laf
    -0.11
     owing
    -0.10
    aina
    -0.10
    due
    -0.10
     Due
    -0.10
     brut
    -0.10
    ucch
    -0.09
    sb
    -0.09
    POSITIVE LOGITS
     nor
    0.17
     Nor
    0.13
    éĻ¤
    0.12
     considering
    0.11
    nor
    0.11
     except
    0.10
     tb
    0.10
    wang
    0.10
    Unless
    0.10
     muse
    0.09
    Activations Density 0.083%

    No Known Activations