© 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. 25990
    Prev
    Next
    INDEX
    Explanations

    quoted text separators

    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
    baugh
    -0.11
    oad
    -0.11
    enden
    -0.11
     PÃ¥
    -0.10
    <strong
    -0.10
    Porno
    -0.10
    >*/↵
    -0.10
     Paperback
    -0.10
    "*
    -0.10
     Klaus
    -0.10
    POSITIVE LOGITS
     Duch
    0.10
    imo
    0.10
    zb
    0.09
     Erd
    0.09
     creeping
    0.08
     Sim
    0.08
     unde
    0.08
    Ĭ
    0.08
     sai
    0.08
     Crom
    0.08
    Activations Density 0.127%

    No Known Activations