© 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. 4027
    Prev
    Next
    INDEX
    Explanations

    70-75-75-

    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
     audition
    -0.08
    Tweet
    -0.08
     Aust
    -0.08
     Buckley
    -0.08
     capped
    -0.08
    .lua
    -0.08
     Avg
    -0.08
     Greene
    -0.08
     Clem
    -0.08
    (o
    -0.08
    POSITIVE LOGITS
     fis
    0.10
    endor
    0.10
    usan
    0.09
     digitally
    0.09
    isman
    0.09
    âĢ¦the
    0.09
     forbid
    0.09
     jur
    0.09
     Fore
    0.09
     hires
    0.09
    Activations Density 0.001%

    No Known Activations