© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 115305
    Prev
    Next
    INDEX
    Explanations

    as you will discover

    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
     disliked
    -0.08
    unga
    -0.08
     Give
    -0.08
     give
    -0.08
     remodel
    -0.08
     Accept
    -0.08
    idl
    -0.08
     Lod
    -0.07
     lent
    -0.07
    ogle
    -0.07
    POSITIVE LOGITS
     pointed
    0.14
     readily
    0.13
     att
    0.13
     demonstrated
    0.13
     well
    0.13
     discovered
    0.12
     demonstrates
    0.11
     happily
    0.11
     demonstrate
    0.11
     evidenced
    0.11
    Activations Density 0.049%

    No Known Activations