© 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. 6841
    Prev
    Next
    INDEX
    Explanations

    template, reusable, substitute

    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
    estre
    -0.10
     transient
    -0.10
     unofficial
    -0.09
    inium
    -0.09
    auc
    -0.09
     Voll
    -0.09
     tentative
    -0.08
     indirect
    -0.08
    ÃŃv
    -0.08
     surpassed
    -0.08
    POSITIVE LOGITS
     reuse
    0.29
     reused
    0.29
     template
    0.28
     substit
    0.27
     templates
    0.27
     substitution
    0.24
     Template
    0.24
     substitute
    0.24
     reusable
    0.24
     substitutions
    0.23
    Activations Density 1.319%

    No Known Activations