© 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. 49508
    Prev
    Next
    INDEX
    Explanations

    Louis, Lesser, General, University, Mode, SD, g, Materials, Class

    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
     ли
    -0.09
     inevitably
    -0.09
     Vs
    -0.08
     Chill
    -0.08
     Everywhere
    -0.08
     Convers
    -0.08
     kla
    -0.08
     Else
    -0.08
     bor
    -0.08
     teg
    -0.08
    POSITIVE LOGITS
     stroke
    0.09
     nug
    0.09
     jewel
    0.09
     sentimental
    0.09
    immel
    0.09
    etch
    0.09
    zl
    0.09
    endi
    0.09
     thread
    0.09
    æĺĵ
    0.09
    Activations Density 0.001%

    No Known Activations