© 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. 28983
    Prev
    Next
    INDEX
    Explanations

    possessive apostrophe ending

    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
     Leeds
    -0.09
     stationary
    -0.08
    ten
    -0.08
    Liked
    -0.08
     Prim
    -0.08
    oret
    -0.08
     det
    -0.08
     Pract
    -0.08
    ermen
    -0.08
    ↵↵↵
    -0.08
    POSITIVE LOGITS
    ÂĢÂĻ
    0.14
    âķĿ
    0.11
     confronting
    0.10
    âķĹ
    0.10
     Kob
    0.10
    âĤ¬âĦ¢
    0.10
    `s
    0.10
    /'
    0.10
    Ìģ
    0.10
    à¹Į
    0.10
    Activations Density 0.040%

    No Known Activations