© 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. 18308
    Prev
    Next
    INDEX
    Explanations

    what's the difference

    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
     themselves
    -0.10
    acic
    -0.09
     Plaza
    -0.09
     Sok
    -0.09
     Bro
    -0.09
     Pel
    -0.08
     Pro
    -0.08
    Pel
    -0.08
     collaborated
    -0.08
     Symbol
    -0.08
    POSITIVE LOGITS
    aben
    0.10
    pler
    0.09
     Od
    0.09
     Traverse
    0.09
     Madd
    0.09
    psc
    0.09
     [#
    0.09
    riot
    0.09
     Matter
    0.08
     matter
    0.08
    Activations Density 0.002%

    No Known Activations