© 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. 49757
    Prev
    Next
    INDEX
    Explanations

    free time

    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
    orman
    -0.12
    574
    -0.12
    oki
    -0.11
    bib
    -0.11
    wat
    -0.11
     limit
    -0.11
     puck
    -0.11
    ikki
    -0.10
    zik
    -0.10
    mpl
    -0.10
    POSITIVE LOGITS
     uninterrupted
    0.10
     coff
    0.10
     guaranteed
    0.10
     awake
    0.08
     uncont
    0.08
     free
    0.08
     contiguous
    0.08
    ief
    0.08
     disposal
    0.08
     Dah
    0.08
    Activations Density 0.043%

    No Known Activations