© 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. 88516
    Prev
    Next
    INDEX
    Explanations

    subscription services

    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
    -0.10
     Shoulder
    -0.10
     hosp
    -0.10
     Euras
    -0.10
     Wide
    -0.09
     deform
    -0.09
     Transformers
    -0.09
     Dai
    -0.09
     paranormal
    -0.09
    OMEM
    -0.09
    POSITIVE LOGITS
     subscription
    0.30
     Subscription
    0.25
     subscriptions
    0.24
    Subscription
    0.21
    subscription
    0.20
     subscribe
    0.18
     subscribers
    0.18
     curated
    0.18
     subscriber
    0.17
     subscribed
    0.17
    Activations Density 0.286%

    No Known Activations