© 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. 113707
    Prev
    Next
    INDEX
    Explanations

    US workers or pair

    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
     MOST
    -0.08
     DEAD
    -0.08
     denn
    -0.07
     scrimmage
    -0.07
    Âł
    -0.07
     âĢķ
    -0.07
     [*
    -0.07
     huh
    -0.07
    _avail
    -0.07
     ÂŃ
    -0.07
    POSITIVE LOGITS
     McCabe
    0.10
    vat
    0.09
     obra
    0.09
     reluctantly
    0.09
     ing
    0.09
    Ľå»º
    0.09
    rud
    0.09
    ofile
    0.09
    .biz
    0.08
    vore
    0.08
    Activations Density 0.614%

    No Known Activations