© 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. 116015
    Prev
    Next
    INDEX
    Explanations

    Department of words

    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
    /host
    -0.08
    oui
    -0.08
     Shed
    -0.08
    HIP
    -0.08
    iele
    -0.07
     kar
    -0.07
    iance
    -0.07
     finishing
    -0.07
     cha
    -0.07
    alem
    -0.07
    POSITIVE LOGITS
     Corrections
    0.14
    artment
    0.14
     Homeland
    0.13
     Commerce
    0.12
    Commerce
    0.11
    avy
    0.11
     Transportation
    0.11
    Weights
    0.11
     Justice
    0.11
     Interior
    0.11
    Activations Density 0.297%

    No Known Activations