© 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. 89020
    Prev
    Next
    INDEX
    Explanations

    discussion topics

    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
     straw
    -0.08
     norms
    -0.08
     rhetoric
    -0.07
     dormant
    -0.07
     Accepted
    -0.07
     underst
    -0.07
    clinic
    -0.07
    ãģ¾
    -0.07
     operative
    -0.07
    igin
    -0.07
    POSITIVE LOGITS
     urgent
    0.22
     wanted
    0.21
     discuss
    0.20
     topics
    0.20
     topic
    0.20
     urgently
    0.20
     matters
    0.19
     agenda
    0.19
     discussing
    0.18
     Wanted
    0.18
    Activations Density 0.215%

    No Known Activations