© 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. 114017
    Prev
    Next
    INDEX
    Explanations

    looking for something

    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
     Garrison
    -0.09
     glad
    -0.09
     impres
    -0.09
     infectious
    -0.09
     erg
    -0.09
    esch
    -0.09
    amel
    -0.08
     disadv
    -0.08
    ersh
    -0.08
     earm
    -0.08
    POSITIVE LOGITS
     quick
    0.15
     reliable
    0.15
     distraction
    0.14
     dose
    0.14
     shortcut
    0.14
     thrill
    0.14
     chance
    0.14
     refund
    0.14
     way
    0.13
     place
    0.13
    Activations Density 0.033%

    No Known Activations