© 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. 30923
    Prev
    Next
    INDEX
    Explanations

    materials are made available

    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
     nip
    -0.10
    oa
    -0.10
     Unsigned
    -0.10
    份
    -0.10
    arter
    -0.09
     Damen
    -0.09
     dormant
    -0.09
     Morm
    -0.09
     Bare
    -0.09
     Bris
    -0.09
    POSITIVE LOGITS
    lime
    0.10
     bul
    0.09
     lime
    0.08
     revel
    0.08
    639
    0.08
     gz
    0.08
    088
    0.08
     Sus
    0.08
     deserving
    0.08
     veloc
    0.08
    Activations Density 0.001%

    No Known Activations