© 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. 6031
    Prev
    Next
    INDEX
    Explanations

    searches the internet and forums

    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
    uber
    -0.10
     chorus
    -0.10
    robe
    -0.10
     prominently
    -0.09
     Problems
    -0.09
    bud
    -0.09
     nearby
    -0.09
    539
    -0.09
    ogram
    -0.09
    =format
    -0.09
    POSITIVE LOGITS
     scour
    0.18
     countless
    0.13
     exhaust
    0.12
     forums
    0.12
     obscure
    0.12
     Forums
    0.12
     sources
    0.12
     tirelessly
    0.11
     continents
    0.11
     oceans
    0.11
    Activations Density 0.080%

    No Known Activations