© 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. 33003
    Prev
    Next
    INDEX
    Explanations

    equilateral, application log, wavelength channel, active carbon, fuel injection, Gaussian mixture, Cancer Centers, Human Development

    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
    imals
    -0.09
     decimals
    -0.09
    icals
    -0.08
     lou
    -0.08
     tr
    -0.08
    edics
    -0.08
    aut
    -0.08
    ி
    -0.07
    rud
    -0.07
    rina
    -0.07
    POSITIVE LOGITS
     Svens
    0.11
     '",
    0.11
    ERRU
    0.11
    TextNode
    0.10
     mastur
    0.10
    lemen
    0.10
    atform
    0.10
    ursal
    0.10
     Zombie
    0.10
     Adler
    0.10
    Activations Density 3.375%

    No Known Activations