© 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. 49175
    Prev
    Next
    INDEX
    Explanations

    see license

    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
     altern
    -0.08
     rounds
    -0.08
    edd
    -0.07
    changed
    -0.07
     fem
    -0.07
    -Mart
    -0.07
     collisions
    -0.07
     fputs
    -0.07
     underline
    -0.07
    ople
    -0.07
    POSITIVE LOGITS
    laps
    0.11
    amps
    0.11
     Garn
    0.10
     Gol
    0.10
    hes
    0.10
     stylist
    0.09
     Ort
    0.09
    chein
    0.09
     Hamp
    0.09
     traf
    0.09
    Activations Density 0.518%

    No Known Activations