© 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. 114332
    Prev
    Next
    INDEX
    Explanations

    post-disaster effects and recovery

    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
    Abort
    -0.10
     oblig
    -0.09
    ár
    -0.09
    blas
    -0.09
    antas
    -0.09
     diag
    -0.09
     UPS
    -0.09
    HTTPRequest
    -0.09
    antan
    -0.09
     Yong
    -0.09
    POSITIVE LOGITS
     recovering
    0.39
     aftermath
    0.38
     recovery
    0.34
     recovered
    0.32
     Recover
    0.31
     damaged
    0.31
     wounded
    0.30
     injured
    0.29
     survivors
    0.29
     Recovery
    0.29
    Activations Density 0.736%

    No Known Activations