© 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. 14836
    Prev
    Next
    INDEX
    Explanations

    recover, overcome, regain

    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
     prot
    -0.09
     Sylv
    -0.09
     Argument
    -0.08
     hy
    -0.08
     perce
    -0.07
     asynchronously
    -0.07
     fus
    -0.07
     Richt
    -0.07
     perceived
    -0.07
     repetitive
    -0.07
    POSITIVE LOGITS
     recover
    0.20
     regained
    0.20
     recovered
    0.20
     Recover
    0.20
     sober
    0.20
     recovering
    0.19
     regain
    0.19
     overcome
    0.19
     overcoming
    0.19
     compose
    0.19
    Activations Density 0.068%

    No Known Activations