© 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. 90813
    Prev
    Next
    INDEX
    Explanations

    anthrop- prefixes

    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
    abilities
    -0.11
    endo
    -0.11
    keepers
    -0.11
    enti
    -0.11
     lest
    -0.10
    cis
    -0.10
     darkest
    -0.10
    osi
    -0.10
    elden
    -0.10
    ete
    -0.09
    POSITIVE LOGITS
     Moss
    0.09
     sank
    0.08
     wig
    0.08
    tram
    0.08
    angen
    0.08
    /dev
    0.08
     Suzuki
    0.08
    /ad
    0.07
    /fr
    0.07
     stiff
    0.07
    Activations Density 0.002%

    No Known Activations