© 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. 49916
    Prev
    Next
    INDEX
    Explanations

    nearing or halfway progress

    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
    cher
    -0.10
     propensity
    -0.09
     season
    -0.09
     aftermath
    -0.09
    ilen
    -0.09
     returned
    -0.09
     spi
    -0.08
     extinct
    -0.08
    zar
    -0.08
     McKenzie
    -0.08
    POSITIVE LOGITS
     progress
    0.38
     Progress
    0.33
     nearing
    0.31
     halfway
    0.30
    progress
    0.29
    Progress
    0.29
    -progress
    0.27
     progressed
    0.25
     progresses
    0.25
     progressing
    0.25
    Activations Density 0.469%

    No Known Activations