© 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. 26752
    Prev
    Next
    INDEX
    Explanations

    followed by comma or period

    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
    lint
    -0.09
    itet
    -0.09
    Ack
    -0.09
    orta
    -0.08
    iland
    -0.08
     cran
    -0.08
     bul
    -0.08
     ack
    -0.08
    trl
    -0.08
     prim
    -0.08
    POSITIVE LOGITS
     Rosenberg
    0.11
     evangel
    0.09
     Heath
    0.09
     bro
    0.09
    /if
    0.09
    áºŃt
    0.09
    usch
    0.09
     Apart
    0.09
    adia
    0.09
    INE
    0.08
    Activations Density 0.001%

    No Known Activations