© 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. 116042
    Prev
    Next
    INDEX
    Explanations

    recovery and rehabilitation

    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
     stamp
    -0.10
    idon
    -0.10
     yearly
    -0.10
    Tonight
    -0.09
     Tonight
    -0.09
     expansion
    -0.09
     Trem
    -0.09
     quarterly
    -0.09
     annual
    -0.09
    Attr
    -0.09
    POSITIVE LOGITS
     recovery
    0.39
     Recovery
    0.36
     recuper
    0.32
     recovering
    0.31
     recover
    0.31
     healing
    0.30
     rehabilitation
    0.30
     Recover
    0.28
     recovered
    0.27
    _recovery
    0.27
    Activations Density 0.405%

    No Known Activations