© 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. 25817
    Prev
    Next
    INDEX
    Explanations

    conditional explanations

    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
     AGAIN
    -0.11
    anza
    -0.11
    itten
    -0.10
    åĬŁ
    -0.10
     Shades
    -0.10
    maj
    -0.09
    zend
    -0.09
    Brief
    -0.09
    anten
    -0.09
     Comments
    -0.09
    POSITIVE LOGITS
     according
    0.11
     exempl
    0.10
     ours
    0.10
     apparently
    0.10
    Meet
    0.09
    .EXP
    0.09
     starring
    0.09
    according
    0.09
     evidently
    0.09
     protagonist
    0.09
    Activations Density 0.347%

    No Known Activations