© 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. 89474
    Prev
    Next
    INDEX
    Explanations

    date and numeric identifiers

    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
    /groups
    -0.09
     overcoming
    -0.09
     InvalidArgumentException
    -0.09
     whence
    -0.09
    adr
    -0.09
     piece
    -0.09
     manifest
    -0.09
     Lama
    -0.09
     unp
    -0.09
     Dawn
    -0.09
    POSITIVE LOGITS
    CCI
    0.12
     politic
    0.09
    ffc
    0.09
     CIT
    0.08
     Manning
    0.08
     Race
    0.08
    alto
    0.08
    544
    0.08
     supposedly
    0.08
     featured
    0.08
    Activations Density 0.013%

    No Known Activations