© 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. 116322
    Prev
    Next
    INDEX
    Explanations

    legal, license, copyright

    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
    pedia
    -0.10
    Twitter
    -0.09
    otime
    -0.09
    erna
    -0.09
     archive
    -0.09
    uzz
    -0.08
     bookmark
    -0.08
    yclopedia
    -0.08
     pew
    -0.08
     forums
    -0.08
    POSITIVE LOGITS
    indr
    0.12
     personals
    0.12
     Valentine
    0.12
     requests
    0.11
     AMA
    0.11
     announcements
    0.10
     exchanging
    0.10
    .nc
    0.10
     adul
    0.10
     Requests
    0.10
    Activations Density 0.018%

    No Known Activations