© 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. 17079
    Prev
    Next
    INDEX
    Explanations

    names followed by relationships or events

    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
    IFn
    -0.09
     impro
    -0.09
     liberties
    -0.08
     Dai
    -0.08
     consequ
    -0.08
     Cin
    -0.08
     Chapman
    -0.08
     Voll
    -0.08
    kah
    -0.08
     Uk
    -0.08
    POSITIVE LOGITS
     twin
    0.11
     Loving
    0.11
     honeymoon
    0.11
     divorced
    0.10
    ibling
    0.10
     RV
    0.10
    joint
    0.10
     meet
    0.10
     LIVE
    0.09
     Meet
    0.09
    Activations Density 0.082%

    No Known Activations