© 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. 17838
    Prev
    Next
    INDEX
    Explanations

    code structure elements

    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
     incon
    -0.08
     utilized
    -0.08
     excell
    -0.08
     mankind
    -0.08
    aved
    -0.08
     Essentially
    -0.08
     profess
    -0.08
     essentially
    -0.07
     jov
    -0.07
    ankind
    -0.07
    POSITIVE LOGITS
     Wich
    0.14
     mini
    0.12
     enthus
    0.12
     OMG
    0.12
    _then
    0.12
     POV
    0.12
    Oops
    0.11
     amort
    0.11
    ^-
    0.11
     unt
    0.11
    Activations Density 0.020%

    No Known Activations