© 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. 114103
    Prev
    Next
    INDEX
    Explanations

    pondering and thinking abstractly

    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
    umba
    -0.11
     Arte
    -0.10
    Towards
    -0.10
    ï¼Īç¬ij
    -0.10
     Nack
    -0.10
    nth
    -0.10
    ned
    -0.10
     Ist
    -0.10
    archs
    -0.10
     Walker
    -0.10
    POSITIVE LOGITS
     briefly
    0.15
     momentarily
    0.14
     awhile
    0.12
     moment
    0.12
     quickly
    0.11
     pause
    0.10
     Pause
    0.10
     quietly
    0.09
     brief
    0.09
    brief
    0.09
    Activations Density 0.021%

    No Known Activations