© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 27748
    Prev
    Next
    INDEX
    Explanations

    pay for

    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
     unpaid
    -0.11
     dealing
    -0.10
    uci
    -0.10
     fountain
    -0.10
     repayment
    -0.10
     Lakes
    -0.10
     PROT
    -0.09
     trackers
    -0.09
     carrot
    -0.09
    ply
    -0.09
    POSITIVE LOGITS
     subscriptions
    0.13
     access
    0.11
     acess
    0.10
     tickets
    0.10
     acces
    0.10
     each
    0.10
    /licenses
    0.09
     dearly
    0.09
    rand
    0.09
     accessing
    0.09
    Activations Density 0.009%

    No Known Activations