© 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. 5738
    Prev
    Next
    INDEX
    Explanations

    things and events it

    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
    Liked
    -0.08
     whatever
    -0.08
    .Option
    -0.08
    aeda
    -0.08
     doubles
    -0.08
     Pods
    -0.08
     Fay
    -0.08
     rew
    -0.08
     Levine
    -0.08
     Shame
    -0.08
    POSITIVE LOGITS
     можно
    0.11
     gyr
    0.11
     ent
    0.11
     tempt
    0.11
    407
    0.10
     ens
    0.10
     abound
    0.10
    /people
    0.10
     encompass
    0.10
     people
    0.10
    Activations Density 0.070%

    No Known Activations