© 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. 3677
    Prev
    Next
    INDEX
    Explanations

    "my" followed by proper nouns

    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
     Blogger
    -0.11
     ta
    -0.10
     prin
    -0.10
    ?↵↵↵↵
    -0.10
     prov
    -0.10
    ,...↵
    -0.09
     nuis
    -0.09
    abe
    -0.09
     blogger
    -0.09
     wis
    -0.09
    POSITIVE LOGITS
     OP
    0.12
     ~~
    0.12
     Nope
    0.11
     weir
    0.11
     combo
    0.10
     FML
    0.10
     FW
    0.10
     legit
    0.10
     ðŁij
    0.10
     pupper
    0.10
    Activations Density 0.008%

    No Known Activations