© 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. 89284
    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
    dep
    -0.13
    rox
    -0.13
     Hardy
    -0.11
    /npm
    -0.11
    tries
    -0.10
     Hoe
    -0.10
    AMI
    -0.10
     fortunes
    -0.10
    ÃŃm
    -0.10
     Cobra
    -0.10
    POSITIVE LOGITS
    annis
    0.09
     ere
    0.09
     ISSN
    0.09
     replacing
    0.08
     Blow
    0.08
    aldi
    0.08
     prem
    0.08
    ubb
    0.08
    à¹ĩ
    0.08
    617
    0.08
    Activations Density 0.000%

    No Known Activations