© 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. 117095
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
     inn
    -0.10
     dit
    -0.10
     Sovere
    -0.09
    oldt
    -0.09
     Inn
    -0.09
    stu
    -0.09
     sovereign
    -0.09
    prov
    -0.09
    (fe
    -0.09
     accepted
    -0.09
    POSITIVE LOGITS
     Perc
    0.11
     Beh
    0.09
     Humph
    0.09
     gl
    0.09
     Herc
    0.08
     Conce
    0.08
    oul
    0.08
    geries
    0.08
     Da
    0.08
     Enrique
    0.08
    Activations Density 0.000%

    No Known Activations