© 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. 47521
    Prev
    Next
    INDEX
    Explanations

    my or MYC

    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
     secretly
    -0.12
     covert
    -0.11
     legally
    -0.10
     PREF
    -0.10
     intervening
    -0.10
     restr
    -0.10
     Nab
    -0.10
     dif
    -0.09
     disguise
    -0.09
     illegally
    -0.09
    POSITIVE LOGITS
     curiosity
    0.15
     skepticism
    0.13
     skeptic
    0.12
     skept
    0.12
     inexp
    0.12
     acceptance
    0.12
     myster
    0.11
     scept
    0.11
     mysterious
    0.11
     skeptical
    0.11
    Activations Density 0.064%

    No Known Activations