© 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. 30568
    Prev
    Next
    INDEX
    Explanations

    and more

    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
    onis
    -0.12
    Includes
    -0.11
     blanket
    -0.10
    includes
    -0.10
     includes
    -0.10
     viz
    -0.10
    anto
    -0.10
    INCLUDING
    -0.10
    oldem
    -0.10
     unavoid
    -0.10
    POSITIVE LOGITS
     depending
    0.12
    depending
    0.09
    —all
    0.09
     tailor
    0.09
    ï¼Į并
    0.08
    eter
    0.08
     luc
    0.08
    ork
    0.08
     tid
    0.07
     tailored
    0.07
    Activations Density 0.272%

    No Known Activations