© 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. 18051
    Prev
    Next
    INDEX
    Explanations

    free download or access

    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
    iele
    -0.06
     Guar
    -0.05
     margin
    -0.05
     Chop
    -0.05
     Hamp
    -0.05
     NYPD
    -0.05
     rulers
    -0.05
     Illum
    -0.05
    iter
    -0.05
     hedge
    -0.04
    POSITIVE LOGITS
     download
    0.23
     pdf
    0.21
     Pdf
    0.21
     Download
    0.18
     DOWNLOAD
    0.17
     gratuit
    0.17
    download
    0.16
     apk
    0.16
     Kostenlos
    0.16
     filetype
    0.16
    Activations Density 0.008%

    No Known Activations