© 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. 50306
    Prev
    Next
    INDEX
    Explanations

    recently started a new phase

    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
     tomorrow
    -0.11
     unseen
    -0.09
    Tomorrow
    -0.08
     Tomorrow
    -0.08
     distract
    -0.08
     distracted
    -0.08
     interrupted
    -0.08
     ordinarily
    -0.08
    isor
    -0.08
     pockets
    -0.08
    POSITIVE LOGITS
     becoming
    0.25
     became
    0.24
     Became
    0.22
    bec
    0.22
     become
    0.22
     newfound
    0.20
     Become
    0.19
     discovered
    0.18
     began
    0.18
     becomes
    0.18
    Activations Density 0.295%

    No Known Activations