© 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. 4788
    Prev
    Next
    INDEX
    Explanations

    copyright or intellectual property rights

    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
    ascar
    -0.10
    -ob
    -0.10
     Quad
    -0.09
    chet
    -0.09
    etch
    -0.09
    vang
    -0.09
     Wit
    -0.09
    arie
    -0.09
     Residential
    -0.09
     quad
    -0.09
    POSITIVE LOGITS
    —to
    0.12
    ,to
    0.11
    omm
    0.10
     Spar
    0.09
    ouro
    0.09
    nc
    0.09
    opy
    0.09
     Jame
    0.09
     Jab
    0.09
    /to
    0.09
    Activations Density 1.795%

    No Known Activations