© 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. 112662
    Prev
    Next
    INDEX
    Explanations

    furans, pacific islanders, periungual

    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
     beaut
    -0.09
    rale
    -0.09
    ftar
    -0.08
    uka
    -0.08
    undry
    -0.08
    fits
    -0.08
    antom
    -0.07
    cket
    -0.07
    .Net
    -0.07
     unnamed
    -0.07
    POSITIVE LOGITS
     Pey
    0.10
    =-=-
    0.10
    )[-
    0.09
    _intersection
    0.09
    asl
    0.08
     PCs
    0.08
     Bram
    0.08
     Cath
    0.08
     PPP
    0.08
    êt
    0.08
    Activations Density 0.019%

    No Known Activations