© 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. 6768
    Prev
    Next
    INDEX
    Explanations

    verb then preposition/article

    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
     congr
    -0.13
     YOUR
    -0.12
     kino
    -0.11
     sluts
    -0.11
     cuckold
    -0.11
     yourself
    -0.11
     gangbang
    -0.11
     yourselves
    -0.11
     your
    -0.10
     ваÑĪ
    -0.10
    POSITIVE LOGITS
     vaguely
    0.17
     my
    0.11
     indign
    0.11
     (“
    0.10
     mourn
    0.10
     assorted
    0.10
     (!
    0.10
     chez
    0.10
     plaint
    0.10
    Tiny
    0.10
    Activations Density 0.005%

    No Known Activations