© 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. 4266
    Prev
    Next
    INDEX
    Explanations

    Hugh followed by names

    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
     cynical
    -0.10
     conc
    -0.10
     precarious
    -0.10
    utto
    -0.10
     bib
    -0.10
     regret
    -0.10
     Rift
    -0.09
     Made
    -0.09
    oux
    -0.09
     Lak
    -0.09
    POSITIVE LOGITS
    illez
    0.09
    ulia
    0.09
     unders
    0.08
     gn
    0.08
    inka
    0.08
    beck
    0.08
     Duel
    0.08
    umer
    0.08
    laden
    0.08
    idebar
    0.07
    Activations Density 0.003%

    No Known Activations