© 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. 117044
    Prev
    Next
    INDEX
    Explanations

    Marco names

    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
     smack
    -0.11
     zer
    -0.10
     plat
    -0.09
     Walter
    -0.09
    oka
    -0.09
    andro
    -0.09
    enda
    -0.09
     Bor
    -0.09
     scop
    -0.09
     Aires
    -0.09
    POSITIVE LOGITS
    ouden
    0.11
     counters
    0.10
    indh
    0.10
     Ritch
    0.09
    bon
    0.09
     tanto
    0.09
     doubly
    0.09
     resumes
    0.09
    erti
    0.09
    acier
    0.09
    Activations Density 0.002%

    No Known Activations