© 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. 4504
    Prev
    Next
    INDEX
    Explanations

    informing or telling users

    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
     cord
    -0.08
     pleasing
    -0.08
     cath
    -0.08
    ets
    -0.08
     Cath
    -0.08
    agen
    -0.08
    owski
    -0.08
    enson
    -0.08
    884
    -0.08
    orden
    -0.08
    POSITIVE LOGITS
     us
    0.17
     him
    0.14
    922
    0.11
    solver
    0.10
    him
    0.10
     bout
    0.10
    ankan
    0.10
    'on
    0.10
    umo
    0.10
     users
    0.09
    Activations Density 0.281%

    No Known Activations