© 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. 27711
    Prev
    Next
    INDEX
    Explanations

    caring for

    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
     Riverside
    -0.10
     pled
    -0.08
     consolid
    -0.08
     ev
    -0.08
     delivering
    -0.08
     fixing
    -0.08
     planning
    -0.08
    upon
    -0.08
     Amar
    -0.07
     settling
    -0.07
    POSITIVE LOGITS
    iasm
    0.12
    ed
    0.11
     cared
    0.11
     dist
    0.10
    bah
    0.10
     accounted
    0.10
    orent
    0.10
     Unsafe
    0.10
     properly
    0.10
    ouri
    0.10
    Activations Density 0.011%

    No Known Activations