© 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. 16063
    Prev
    Next
    INDEX
    Explanations

    may you do good

    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
     shameful
    -0.09
     systematically
    -0.08
     reliably
    -0.08
     Late
    -0.08
     voluntarily
    -0.08
    -c
    -0.08
     certain
    -0.07
     swo
    -0.07
     lament
    -0.07
    wd
    -0.07
    POSITIVE LOGITS
     wherever
    0.20
     whichever
    0.15
     prosperous
    0.13
     endeavors
    0.13
     whatever
    0.13
    akra
    0.13
     prosperity
    0.13
     prosper
    0.12
     onward
    0.12
     Karma
    0.12
    Activations Density 0.071%

    No Known Activations