© 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. 13945
    Prev
    Next
    INDEX
    Explanations

    "say" followed by names or quotes

    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
     saying
    -0.14
     Saying
    -0.12
    says
    -0.11
    ered
    -0.10
    ead
    -0.10
    blick
    -0.10
    kre
    -0.09
     says
    -0.09
     say
    -0.09
    isers
    -0.09
    POSITIVE LOGITS
     goodbye
    0.26
     aloud
    0.19
    /write
    0.17
     farewell
    0.17
     hello
    0.15
    æľį
    0.15
    ings
    0.14
    umpt
    0.14
    /show
    0.14
    /do
    0.13
    Activations Density 0.109%

    No Known Activations