© 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. 88569
    Prev
    Next
    INDEX
    Explanations

    numeric expressions with commas

    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
     elite
    -0.09
    UU
    -0.08
     unm
    -0.08
    rit
    -0.08
    Uno
    -0.08
    ellen
    -0.08
    eti
    -0.08
     uy
    -0.08
     trad
    -0.07
     departed
    -0.07
    POSITIVE LOGITS
     {:.
    0.13
     (.
    0.10
    aign
    0.10
    {}.
    0.10
    rost
    0.10
     Timothy
    0.10
    dux
    0.10
    osto
    0.09
     Tah
    0.09
     Bend
    0.09
    Activations Density 0.674%

    No Known Activations