© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 114489
    Prev
    Next
    INDEX
    Explanations

    function calls or definitions

    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
    ILT
    -0.09
    205
    -0.09
     INST
    -0.09
     flo
    -0.09
     lut
    -0.08
    .Report
    -0.08
     jig
    -0.08
     Dann
    -0.08
     Kut
    -0.08
    lobal
    -0.08
    POSITIVE LOGITS
    zes
    0.10
     Loose
    0.09
     secretly
    0.09
     Spar
    0.09
     loose
    0.09
     hypnot
    0.09
     Chrysler
    0.09
    .ac
    0.08
    uckland
    0.08
    ¼
    0.08
    Activations Density 0.132%

    No Known Activations