© 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. 14421
    Prev
    Next
    INDEX
    Explanations

    barely, moderately, noticeably

    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
     somehow
    -0.13
     secretly
    -0.09
     someday
    -0.09
     slu
    -0.09
     since
    -0.09
     slag
    -0.09
     Boxing
    -0.09
     Whatever
    -0.09
     apparently
    -0.08
    iore
    -0.08
    POSITIVE LOGITS
     moderately
    0.17
     mildly
    0.14
     moderate
    0.13
     noticeably
    0.13
     tested
    0.13
     tests
    0.12
     Bare
    0.12
     testers
    0.12
     barely
    0.12
     readily
    0.12
    Activations Density 0.530%

    No Known Activations