© 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. 32230
    Prev
    Next
    INDEX
    Explanations

    asking Him explain sound good

    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
    izing
    -0.11
    ize
    -0.10
    coni
    -0.10
    /interface
    -0.10
     Incident
    -0.10
    izable
    -0.10
    elf
    -0.10
    hil
    -0.10
    iores
    -0.09
    zia
    -0.09
    POSITIVE LOGITS
    ened
    0.09
     awhile
    0.09
    liest
    0.09
    енÑĮ
    0.09
     enchanted
    0.08
    ster
    0.08
     victorious
    0.08
     upon
    0.08
     Hutch
    0.08
     unw
    0.08
    Activations Density 0.263%

    No Known Activations