© 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. 17815
    Prev
    Next
    INDEX
    Explanations

    hotel types, gender, or star ratings

    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
    Uvs
    -0.10
     Situation
    -0.10
     wann
    -0.09
    roids
    -0.09
    iaux
    -0.09
     Ler
    -0.09
     situation
    -0.09
    asser
    -0.09
    .bmp
    -0.09
     Sund
    -0.09
    POSITIVE LOGITS
     female
    0.11
    isz
    0.10
     girl
    0.10
     misc
    0.09
    arent
    0.09
     taller
    0.09
    Misc
    0.09
    attr
    0.09
     Misc
    0.09
    hf
    0.09
    Activations Density 0.025%

    No Known Activations