© 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. 28892
    Prev
    Next
    INDEX
    Explanations

    atop, alongside, aboard

    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
     lacking
    -0.08
     clos
    -0.08
     absence
    -0.08
    uits
    -0.08
    atica
    -0.08
     Cah
    -0.08
    KEEP
    -0.08
     up
    -0.08
    kas
    -0.08
    E
    -0.07
    POSITIVE LOGITS
    iard
    0.10
    iform
    0.10
    OfClass
    0.09
    yy
    0.09
    tempt
    0.09
    /on
    0.09
    ocz
    0.09
     stil
    0.09
     wall
    0.09
    secondary
    0.09
    Activations Density 0.009%

    No Known Activations