© 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. 30035
    Prev
    Next
    INDEX
    Explanations

    off-thread, game changer, cutting edge, step up

    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
     secluded
    -0.10
     singled
    -0.10
     bustling
    -0.09
     recl
    -0.09
     disgrace
    -0.09
     literally
    -0.09
     likeness
    -0.09
     physically
    -0.09
     filmy
    -0.09
     feats
    -0.08
    POSITIVE LOGITS
     bricks
    0.12
    wrap
    0.11
     wrap
    0.11
     ful
    0.11
     nails
    0.11
     mojo
    0.11
     Camel
    0.11
     odom
    0.11
     vanilla
    0.11
     camel
    0.11
    Activations Density 0.428%

    No Known Activations