© 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. 49082
    Prev
    Next
    INDEX
    Explanations

    reverse or inverse operations

    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
    warts
    -0.10
    lates
    -0.09
    jo
    -0.09
     drip
    -0.09
    mit
    -0.09
    ties
    -0.09
    MIT
    -0.09
     Baghdad
    -0.08
     peel
    -0.08
     burge
    -0.08
    POSITIVE LOGITS
    arde
    0.11
    elay
    0.10
     Hoy
    0.10
     requis
    0.09
     Dun
    0.09
    .sync
    0.08
     concession
    0.08
    ddb
    0.08
    shaw
    0.08
     Reb
    0.08
    Activations Density 0.004%

    No Known Activations