© 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. 116075
    Prev
    Next
    INDEX
    Explanations

    content related to articles or posts

    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
     :</
    -0.09
    ero
    -0.09
     cong
    -0.08
    ÃĤ
    -0.08
     mou
    -0.08
     :\
    -0.08
     Lad
    -0.08
     fabric
    -0.07
     Rus
    -0.07
     spark
    -0.07
    POSITIVE LOGITS
     under
    0.15
     dated
    0.14
     therein
    0.14
     archived
    0.13
     posted
    0.13
     listed
    0.13
     labeled
    0.13
     yourselves
    0.12
     beginning
    0.12
     scroll
    0.12
    Activations Density 0.323%

    No Known Activations