© 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. 28169
    Prev
    Next
    INDEX
    Explanations

    greek or latin suffixes

    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
     Jeb
    -0.09
     upside
    -0.09
    edImage
    -0.07
     Grandma
    -0.07
     though
    -0.07
     Lodge
    -0.07
     additionally
    -0.07
     unh
    -0.07
    athi
    -0.07
     deterministic
    -0.07
    POSITIVE LOGITS
     convenient
    0.11
     Convenient
    0.10
     paar
    0.09
     spontaneous
    0.09
    quo
    0.08
    DataSetChanged
    0.08
    füg
    0.08
     handy
    0.08
     hj
    0.08
    gow
    0.08
    Activations Density 1.961%

    No Known Activations