© 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. 5268
    Prev
    Next
    INDEX
    Explanations

    contribution and support

    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
     Ari
    -0.10
     Ard
    -0.10
     ard
    -0.09
     Soph
    -0.09
     volum
    -0.09
    enen
    -0.08
    /apis
    -0.08
     GT
    -0.08
     scr
    -0.08
    aras
    -0.08
    POSITIVE LOGITS
     Together
    0.26
     together
    0.26
    Together
    0.26
     Help
    0.20
     help
    0.18
     contribution
    0.18
    Help
    0.18
    help
    0.17
     Contributions
    0.17
     helping
    0.16
    Activations Density 0.276%

    No Known Activations