© 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. 30648
    Prev
    Next
    INDEX
    Explanations

    mathematical formulas

    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
     renew
    -0.12
     Mos
    -0.11
     Cant
    -0.11
     Mona
    -0.11
     cane
    -0.10
    jom
    -0.10
    acco
    -0.10
    icha
    -0.10
     rev
    -0.10
     Arnold
    -0.10
    POSITIVE LOGITS
     AU
    0.09
    “
    0.09
    .“
    0.09
     curated
    0.08
     Warm
    0.08
     fucking
    0.08
     fic
    0.08
     Oro
    0.07
     (“
    0.07
     Toro
    0.07
    Activations Density 0.003%

    No Known Activations