© 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. 25691
    Prev
    Next
    INDEX
    Explanations

    permissions and limitations under

    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
     Kaiser
    -0.10
     schl
    -0.08
    reich
    -0.08
     Ann
    -0.08
    boxes
    -0.07
     spur
    -0.07
     tables
    -0.07
     krist
    -0.07
     Altern
    -0.07
    esa
    -0.07
    POSITIVE LOGITS
    ereg
    0.11
     nationally
    0.11
    oi
    0.11
     Flam
    0.10
    anced
    0.10
     %@
    0.10
    anko
    0.10
    ede
    0.10
     sidel
    0.10
    lle
    0.10
    Activations Density 0.001%

    No Known Activations