© 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. 91950
    Prev
    Next
    INDEX
    Explanations

    JSON object structures

    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
     Depths
    -0.08
    rees
    -0.07
     ham
    -0.07
     Ivory
    -0.07
    ainment
    -0.07
    .Env
    -0.07
    hips
    -0.06
     Sanford
    -0.06
    hip
    -0.06
     mus
    -0.06
    POSITIVE LOGITS
    ÑĤи
    0.11
     dign
    0.11
     Femin
    0.11
     Geh
    0.11
     daycare
    0.11
    oa
    0.11
     catering
    0.11
    cli
    0.10
     Ung
    0.10
    izzo
    0.10
    Activations Density 0.005%

    No Known Activations