© 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. 27680
    Prev
    Next
    INDEX
    Explanations

    end of phrases

    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
     chose
    -0.15
     preferring
    -0.13
     prefers
    -0.13
     forgot
    -0.13
     lia
    -0.13
     hoping
    -0.12
     refuse
    -0.12
     saying
    -0.12
     spends
    -0.12
     chooses
    -0.12
    POSITIVE LOGITS
     prompting
    0.15
     cul
    0.14
     underscore
    0.11
     necess
    0.11
     encompass
    0.11
     whereby
    0.10
     interrupted
    0.10
     prompted
    0.09
     with
    0.09
     lasted
    0.09
    Activations Density 0.353%

    No Known Activations