© 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. 113895
    Prev
    Next
    INDEX
    Explanations

    instead

    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
     none
    -0.10
     neither
    -0.10
    ении
    -0.10
    /generated
    -0.09
     None
    -0.09
    ä»Ĭå¹´
    -0.09
    Repositories
    -0.09
     fourteen
    -0.09
     Ordering
    -0.09
    ansa
    -0.09
    POSITIVE LOGITS
     somehow
    0.20
     Somehow
    0.16
     suddenly
    0.16
     Suddenly
    0.13
     somewhere
    0.12
    Suddenly
    0.12
     instead
    0.12
     society
    0.12
     Instead
    0.11
    instead
    0.11
    Activations Density 0.356%

    No Known Activations