© 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. 13913
    Prev
    Next
    INDEX
    Explanations

    don't verbs

    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
    Negative Logits
     Eins
    -0.12
    partials
    -0.10
    aren
    -0.10
    ][/
    -0.09
     Matth
    -0.09
    à¸ĵ
    -0.09
    ret
    -0.09
     Dover
    -0.09
     Mund
    -0.09
    conti
    -0.09
    POSITIVE LOGITS
     suppose
    0.16
     know
    0.14
     think
    0.13
     mean
    0.13
    think
    0.13
     envy
    0.12
     recall
    0.10
     Suppose
    0.10
     THINK
    0.10
     sure
    0.10
    Activations Density 0.035%

    No Known Activations