© 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. 27757
    Prev
    Next
    INDEX
    Explanations

    finally, sometime, someday

    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
    zo
    -0.10
    ÃĦ
    -0.10
     Tee
    -0.10
    isas
    -0.09
     Graham
    -0.09
     due
    -0.09
    oba
    -0.09
    319
    -0.09
     dilig
    -0.09
     Rubio
    -0.09
    POSITIVE LOGITS
     instead
    0.15
     sometime
    0.15
     finally
    0.15
    instead
    0.14
     someday
    0.14
     atleast
    0.14
     decent
    0.13
     lest
    0.13
     occasional
    0.13
     besides
    0.12
    Activations Density 0.246%

    No Known Activations