© 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. 117100
    Prev
    Next
    INDEX
    Explanations

    int, inst, im, i prefixes followed by various endings

    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
    iler
    -0.09
     Dre
    -0.09
    ashes
    -0.09
    ils
    -0.08
     commanding
    -0.08
     profound
    -0.08
     kenn
    -0.08
     hol
    -0.08
     scarcity
    -0.07
     phil
    -0.07
    POSITIVE LOGITS
    mediate
    0.14
     incremental
    0.14
     inauguration
    0.13
    rastructure
    0.13
    redients
    0.13
     Inspiration
    0.13
     infield
    0.13
     Investigations
    0.13
     Infrastructure
    0.13
    itial
    0.13
    Activations Density 0.426%

    No Known Activations