© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 48517
    Prev
    Next
    INDEX
    Explanations

    Indiana Jones

    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
    emy
    -0.08
     Enjoy
    -0.07
    aint
    -0.07
     bypass
    -0.07
    lua
    -0.07
     Apprec
    -0.07
     unconscious
    -0.07
     Wonderful
    -0.07
     implicit
    -0.07
     Gone
    -0.06
    POSITIVE LOGITS
    oice
    0.12
    oy
    0.11
    Bins
    0.10
     aide
    0.10
    olum
    0.10
    olin
    0.10
     sweat
    0.10
    /vendors
    0.10
     Rou
    0.10
     bre
    0.09
    Activations Density 0.002%

    No Known Activations