© 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. 47293
    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
    ois
    -0.11
    irs
    -0.10
     residual
    -0.10
    [s
    -0.09
     Buckley
    -0.09
    tors
    -0.09
    ths
    -0.09
     invites
    -0.08
     undeniable
    -0.08
    �s
    -0.08
    POSITIVE LOGITS
     hypoth
    0.09
     Kata
    0.09
     reversing
    0.09
    /feed
    0.09
     Din
    0.09
    elah
    0.09
    chrift
    0.08
     Rex
    0.08
     thresh
    0.08
    Dry
    0.08
    Activations Density 0.000%

    No Known Activations