© 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. 117194
    Prev
    Next
    INDEX
    Explanations

    days, months, and times

    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
     anyhow
    -0.09
     colum
    -0.09
     Dear
    -0.09
     Modules
    -0.08
    /Search
    -0.08
    agger
    -0.08
     clipped
    -0.08
     Colum
    -0.08
    hear
    -0.08
     farther
    -0.07
    POSITIVE LOGITS
     onwards
    0.18
     onward
    0.13
     evening
    0.12
    onus
    0.12
    izr
    0.11
     morning
    0.10
     hustle
    0.10
     happiest
    0.10
    567
    0.10
    busy
    0.10
    Activations Density 0.231%

    No Known Activations