© 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. 114404
    Prev
    Next
    INDEX
    Explanations

    is/are [word]

    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
     differing
    -0.08
     âĢİ
    -0.08
     Spit
    -0.08
    zer
    -0.08
     pec
    -0.08
     BILL
    -0.08
     pont
    -0.07
     negligent
    -0.07
     Acts
    -0.07
    unable
    -0.07
    POSITIVE LOGITS
     swell
    0.16
     underrated
    0.15
     supposed
    0.15
     meant
    0.14
     fun
    0.14
     cooler
    0.14
     worth
    0.13
     scary
    0.13
     cool
    0.13
     spelled
    0.13
    Activations Density 0.095%

    No Known Activations