© 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. 27530
    Prev
    Next
    INDEX
    Explanations

    links, examples, headers

    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
    ilos
    -0.12
     Conrad
    -0.11
    esub
    -0.11
     esac
    -0.11
     Kits
    -0.11
    ’e
    -0.11
     ini
    -0.10
    olib
    -0.10
    kits
    -0.10
     Hawth
    -0.10
    POSITIVE LOGITS
     soften
    0.07
     Shelter
    0.06
     Austral
    0.06
     ...↵↵
    0.06
     ``
    0.06
     fle
    0.06
     unsur
    0.06
     Unicorn
    0.06
     ign
    0.06
     Secondary
    0.06
    Activations Density 0.003%

    No Known Activations