© 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. 48006
    Prev
    Next
    INDEX
    Explanations

    meta tags, long descriptions, Robert Mugabe

    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
    assen
    -0.08
     Unsure
    -0.08
    esture
    -0.08
    alis
    -0.08
    .SubElement
    -0.08
     precise
    -0.08
    Contained
    -0.08
     sca
    -0.08
    ridged
    -0.08
    fir
    -0.08
    POSITIVE LOGITS
     Kö
    0.07
    .setDefault
    0.06
     Pornhub
    0.06
    ByPrimaryKey
    0.06
    ="#"
    0.06
     nostalg
    0.06
    baz
    0.06
     minut
    0.06
    .deb
    0.05
     excell
    0.05
    Activations Density 3.914%

    No Known Activations