© 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. 32788
    Prev
    Next
    INDEX
    Explanations

    non-volatile

    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
     misunder
    -0.12
     skl
    -0.09
    -or
    -0.09
    inals
    -0.09
     impost
    -0.09
    FA
    -0.09
     misd
    -0.09
     mav
    -0.09
    imals
    -0.09
     Offices
    -0.09
    POSITIVE LOGITS
    bek
    0.10
    ijke
    0.10
     Lan
    0.09
    Overview
    0.09
     Jr
    0.09
     suite
    0.09
    938
    0.09
     rev
    0.09
    oyer
    0.09
    aky
    0.09
    Activations Density 0.038%

    No Known Activations