© 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. 30974
    Prev
    Next
    INDEX
    Explanations

    put in action

    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
     onto
    -0.13
     atop
    -0.09
    sand
    -0.09
     Dies
    -0.08
    .AddListener
    -0.08
    cir
    -0.08
     conformity
    -0.08
    .gdx
    -0.08
    Å¡t
    -0.08
    585
    -0.08
    POSITIVE LOGITS
     requests
    0.17
     request
    0.17
     orders
    0.15
     bids
    0.14
     Orders
    0.14
     Requests
    0.14
     bid
    0.14
     effort
    0.13
     appearances
    0.13
    requests
    0.13
    Activations Density 0.030%

    No Known Activations