© 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. 31054
    Prev
    Next
    INDEX
    Explanations

    Redistributions in

    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
     Benn
    -0.09
     insights
    -0.08
    ildo
    -0.08
    aye
    -0.08
    apol
    -0.08
     Gund
    -0.08
     Sung
    -0.08
    ilos
    -0.08
     yarn
    -0.08
     sino
    -0.08
    POSITIVE LOGITS
    Queryable
    0.10
     fet
    0.10
    Establish
    0.10
    wed
    0.09
     confident
    0.09
    bine
    0.09
     hone
    0.09
    chor
    0.09
     Establish
    0.09
     racked
    0.09
    Activations Density 0.001%

    No Known Activations