© 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. 47467
    Prev
    Next
    INDEX
    Explanations

    biological and chemical activities

    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
    .HttpServletResponse
    -0.07
     clip
    -0.07
    (library
    -0.07
    chie
    -0.06
     ï
    -0.06
     epis
    -0.06
     viable
    -0.06
    né
    -0.06
     EXT
    -0.06
     bureaucracy
    -0.06
    POSITIVE LOGITS
     biod
    0.12
    Plugins
    0.11
    fade
    0.10
     achter
    0.10
    _forum
    0.10
    ÑĤа
    0.10
     shoulders
    0.10
     Erotik
    0.10
     rampage
    0.10
     Legend
    0.10
    Activations Density 0.220%

    No Known Activations