© 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. 17872
    Prev
    Next
    INDEX
    Explanations

    legal counsel and advising

    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
    aty
    -0.09
     Ly
    -0.08
     Dream
    -0.08
     prick
    -0.08
     scratch
    -0.08
     MST
    -0.08
    obe
    -0.08
    ür
    -0.08
     mobil
    -0.07
     Kob
    -0.07
    POSITIVE LOGITS
    passport
    0.10
     Hardcover
    0.10
     intellectually
    0.10
     Entr
    0.10
     Ful
    0.10
     Dise
    0.10
     Sever
    0.10
    NOTE
    0.10
    adin
    0.10
     advances
    0.10
    Activations Density 0.001%

    No Known Activations