© 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. 26475
    Prev
    Next
    INDEX
    Explanations

    viewing messages

    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
     lem
    -0.10
     housing
    -0.10
     Twin
    -0.10
    adget
    -0.09
     Housing
    -0.09
    alamat
    -0.09
    uci
    -0.09
     Ses
    -0.09
     Hardy
    -0.09
     soc
    -0.09
    POSITIVE LOGITS
     bipolar
    0.10
    dit
    0.09
     Cra
    0.09
     stray
    0.09
     Balt
    0.09
    .mj
    0.09
    uib
    0.08
    ëĵ
    0.08
     shadows
    0.08
     crab
    0.08
    Activations Density 0.001%

    No Known Activations