© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 15965
    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
     unw
    -0.10
     octave
    -0.09
     Saud
    -0.09
    lok
    -0.09
     cred
    -0.09
     Strand
    -0.09
    /master
    -0.09
     Spar
    -0.09
    ernal
    -0.08
     Pear
    -0.08
    POSITIVE LOGITS
    aca
    0.10
     Yates
    0.09
     procrast
    0.09
    ipi
    0.09
     shame
    0.09
     Casa
    0.09
     Lam
    0.09
     dee
    0.09
    EZ
    0.08
     lam
    0.08
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.