© 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. 31276
    Prev
    Next
    INDEX
    Explanations

    pdf documents

    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
    issant
    -0.09
     Brett
    -0.09
    rouw
    -0.09
    rou
    -0.08
     Lowe
    -0.08
     sty
    -0.08
    .rev
    -0.08
    utes
    -0.07
     wart
    -0.07
     stav
    -0.07
    POSITIVE LOGITS
    417
    0.13
    andom
    0.10
     badly
    0.10
     Equity
    0.09
     vic
    0.09
    abin
    0.09
     pony
    0.09
     Atmos
    0.09
    ÃĤ
    0.09
     Stre
    0.09
    Activations Density 0.013%

    No Known Activations