© 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. 15845
    Prev
    Next
    INDEX
    Explanations

    and then other clauses

    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
    iov
    -0.09
     errone
    -0.09
    oy
    -0.09
    esis
    -0.09
     exception
    -0.09
     lum
    -0.09
    zie
    -0.09
     notice
    -0.09
    endi
    -0.08
     soap
    -0.08
    POSITIVE LOGITS
     hopefully
    0.18
     afterwards
    0.15
     possibly
    0.15
     maybe
    0.13
     Hopefully
    0.13
     afterward
    0.13
     preferably
    0.12
     Possibly
    0.12
    Hopefully
    0.12
     whatever
    0.12
    Activations Density 0.036%

    No Known Activations