© 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. 16421
    Prev
    Next
    INDEX
    Explanations

    educational topics and resources

    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
     ingenious
    -0.10
     devis
    -0.09
     exploiting
    -0.09
     NA
    -0.09
     complain
    -0.09
     complains
    -0.09
     devise
    -0.09
    .strptime
    -0.09
    ennon
    -0.09
    usterity
    -0.09
    POSITIVE LOGITS
     informative
    0.36
     informational
    0.32
     informat
    0.26
     comprehensive
    0.25
     knowledgeable
    0.25
     educating
    0.25
     educ
    0.24
     educate
    0.24
     facts
    0.23
     information
    0.23
    Activations Density 0.613%

    No Known Activations