© 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. 115960
    Prev
    Next
    INDEX
    Explanations

    names like Uelle or Amanita

    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
    esta
    -0.09
     Proceed
    -0.09
    bury
    -0.09
     Creed
    -0.09
    scription
    -0.09
     gall
    -0.08
    bery
    -0.08
    ape
    -0.08
    oser
    -0.08
     Cow
    -0.08
    POSITIVE LOGITS
    uele
    0.15
    uelle
    0.11
     inher
    0.11
    agements
    0.11
    ently
    0.10
    UEL
    0.10
    uell
    0.09
    acs
    0.09
    uela
    0.09
    ENTA
    0.09
    Activations Density 0.049%

    No Known Activations