© 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. 16833
    Prev
    Next
    INDEX
    Explanations

    United States Court

    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
     spre
    -0.10
    Nos
    -0.09
     Rowe
    -0.09
    bish
    -0.09
    squ
    -0.09
    empl
    -0.09
    COPE
    -0.09
     sque
    -0.09
    áf
    -0.09
    chn
    -0.09
    POSITIVE LOGITS
     invis
    0.09
     Persist
    0.09
     /↵↵
    0.08
     unb
    0.08
     ,↵↵
    0.08
     .↵↵
    0.08
     flex
    0.08
    odia
    0.08
    peed
    0.08
     Breath
    0.08
    Activations Density 0.203%

    No Known Activations