© 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. 6418
    Prev
    Next
    INDEX
    Explanations

    names ending in /-alk/, /-all/, /-val/

    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
    quo
    -0.09
     resh
    -0.08
    atives
    -0.08
    udad
    -0.08
     subsequent
    -0.08
     Swe
    -0.07
     dood
    -0.07
     Straw
    -0.07
    TRA
    -0.07
    że
    -0.07
    POSITIVE LOGITS
    bone
    0.10
    ored
    0.09
     discipl
    0.09
    enberg
    0.09
    earch
    0.09
    (er
    0.09
     Majority
    0.09
     pne
    0.09
    oref
    0.09
    ee
    0.09
    Activations Density 0.163%

    No Known Activations