© 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. 115755
    Prev
    Next
    INDEX
    Explanations

    large numbers

    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
     mend
    -0.11
     tent
    -0.10
    000
    -0.10
     rings
    -0.10
    ï¼IJ
    -0.09
    0
    -0.09
     doubled
    -0.09
     traps
    -0.09
    012
    -0.09
    086
    -0.09
    POSITIVE LOGITS
     thousands
    0.20
     thousand
    0.16
    Thousands
    0.15
     Thousands
    0.14
     hundreds
    0.11
     millennia
    0.11
     thous
    0.10
    audi
    0.09
    lite
    0.09
     Bauer
    0.09
    Activations Density 0.160%

    No Known Activations