© 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. 27941
    Prev
    Next
    INDEX
    Explanations

    importance and priority

    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
     Acc
    -0.11
    è¯ģ
    -0.11
     faith
    -0.11
    nak
    -0.10
     ACL
    -0.10
    iska
    -0.10
    itta
    -0.10
    =}
    -0.10
     harmful
    -0.10
    uent
    -0.09
    POSITIVE LOGITS
     priority
    0.38
     priorities
    0.31
     Priority
    0.31
     paramount
    0.30
     priorit
    0.28
     prioritize
    0.28
    priority
    0.26
    Priority
    0.26
     concern
    0.21
     prio
    0.21
    Activations Density 0.143%

    No Known Activations