© 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. 114104
    Prev
    Next
    INDEX
    Explanations

    programmatically construct

    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
     distr
    -0.09
     esteemed
    -0.09
     Arte
    -0.08
     hears
    -0.08
     prest
    -0.08
     Dest
    -0.08
     destabil
    -0.08
     Aub
    -0.08
     Verse
    -0.08
    ioned
    -0.08
    POSITIVE LOGITS
     tone
    0.12
     smirk
    0.11
     mo
    0.11
    -l
    0.10
     Tone
    0.10
     Roths
    0.10
     undert
    0.10
     Watkins
    0.10
     li
    0.10
     intentional
    0.10
    Activations Density 0.001%

    No Known Activations