© 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. 4164
    Prev
    Next
    INDEX
    Explanations

    titles like "king of"

    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
     gim
    -0.11
     scre
    -0.11
     DIY
    -0.10
    rowse
    -0.10
     diy
    -0.10
     GMO
    -0.10
    faction
    -0.10
    /moment
    -0.09
    wert
    -0.09
     frau
    -0.09
    POSITIVE LOGITS
    oz
    0.09
     humanity
    0.08
     Zur
    0.08
    оз
    0.08
    .assignment
    0.08
    unic
    0.07
     advise
    0.07
     Burl
    0.07
     Humanity
    0.07
     bamboo
    0.07
    Activations Density 0.019%

    No Known Activations