© 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. 16372
    Prev
    Next
    INDEX
    Explanations

    you may not

    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
    hw
    -0.09
     Conway
    -0.08
     neh
    -0.08
    ACHI
    -0.08
     unstoppable
    -0.08
    oga
    -0.08
    illis
    -0.08
     unavoidable
    -0.08
     invol
    -0.08
     Fits
    -0.07
    POSITIVE LOGITS
     nor
    0.70
    nor
    0.58
     Nor
    0.57
    Nor
    0.47
     NOR
    0.33
     anymore
    0.31
     sondern
    0.31
     neither
    0.31
     Neither
    0.23
    Neither
    0.22
    Activations Density 1.651%

    No Known Activations