© 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. 4523
    Prev
    Next
    INDEX
    Explanations

    hard to

    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
    ĥģ
    -0.09
     scoff
    -0.08
     cf
    -0.08
     polling
    -0.07
     Ele
    -0.07
    985
    -0.06
     preferably
    -0.06
     Savage
    -0.06
     disgust
    -0.06
     savvy
    -0.06
    POSITIVE LOGITS
     convincing
    0.21
     reconc
    0.19
     balancing
    0.18
     transitions
    0.17
     convince
    0.17
     discern
    0.17
     Maint
    0.17
     resist
    0.17
     Conv
    0.17
     reconcile
    0.16
    Activations Density 0.064%

    No Known Activations