© 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. 46859
    Prev
    Next
    INDEX
    Explanations

    ninth circuit, north carolina

    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
    iera
    -0.09
     accusing
    -0.08
    .She
    -0.08
    oshi
    -0.08
     Lot
    -0.08
    ®
    -0.08
     supp
    -0.08
     thus
    -0.08
     stere
    -0.08
    iez
    -0.08
    POSITIVE LOGITS
    gun
    0.11
     Newsp
    0.10
    -meta
    0.09
     vå
    0.09
     regist
    0.09
    ]+\
    0.09
    owitz
    0.08
    comp
    0.08
     mer
    0.08
    iggins
    0.08
    Activations Density 0.003%

    No Known Activations