© 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. 14856
    Prev
    Next
    INDEX
    Explanations

    minikirt, nanocomposites, min-cut

    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
     increments
    -0.09
     Stam
    -0.09
    âĢİ
    -0.09
    itto
    -0.08
     increment
    -0.08
    avo
    -0.08
    manship
    -0.08
     bord
    -0.08
    zy
    -0.08
    mem
    -0.08
    POSITIVE LOGITS
    uco
    0.11
    ipse
    0.11
     severed
    0.10
     conce
    0.10
    ropp
    0.09
    canonical
    0.09
    rok
    0.09
    orsch
    0.09
     Patch
    0.09
    alah
    0.09
    Activations Density 0.001%

    No Known Activations