© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 7486
    Prev
    Next
    INDEX
    Explanations

    configurations or arrangement styles

    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
     tern
    -0.10
    dess
    -0.10
     Tun
    -0.10
    -lined
    -0.10
    -filled
    -0.09
     lik
    -0.09
    akis
    -0.09
    >:</
    -0.09
     KE
    -0.09
     consec
    -0.09
    POSITIVE LOGITS
     setup
    0.14
     configuration
    0.14
    -style
    0.14
     arrangement
    0.14
     style
    0.13
    -esque
    0.12
     formation
    0.12
     format
    0.11
     fashion
    0.11
     type
    0.11
    Activations Density 0.012%

    No Known Activations