© 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. 47112
    Prev
    Next
    INDEX
    Explanations

    according to

    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
    ict
    -0.10
     conce
    -0.10
    illon
    -0.10
    ids
    -0.10
    bery
    -0.10
    ORED
    -0.10
    eroon
    -0.10
    ued
    -0.10
    amp
    -0.10
    ilon
    -0.10
    POSITIVE LOGITS
     legend
    0.08
    uya
    0.08
    sert
    0.08
     plan
    0.07
    ancy
    0.07
    suite
    0.07
    ool
    0.07
     preference
    0.07
    eous
    0.07
    ately
    0.07
    Activations Density 0.079%

    No Known Activations