© 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. 16819
    Prev
    Next
    INDEX
    Explanations

    describing states of being

    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
     wink
    -0.09
    essential
    -0.08
     Cardinal
    -0.08
     mer
    -0.08
     clinging
    -0.08
     vind
    -0.08
     uncont
    -0.07
     blunt
    -0.07
     Fres
    -0.07
    inity
    -0.07
    POSITIVE LOGITS
     deserted
    0.17
     crowded
    0.17
     bustling
    0.17
     divided
    0.15
     quiet
    0.15
     peaceful
    0.15
     buzzing
    0.15
     busy
    0.14
     calm
    0.13
     quieter
    0.13
    Activations Density 0.096%

    No Known Activations