© 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. 17252
    Prev
    Next
    INDEX
    Explanations

    adverbs qualifying statements

    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
     Ped
    -0.10
    ;i
    -0.09
     ],
    -0.09
    .),
    -0.09
    uba
    -0.09
     Higgins
    -0.09
    :],
    -0.09
    ago
    -0.09
    '],
    -0.09
     -,
    -0.09
    POSITIVE LOGITS
     anyways
    0.08
     Arsenal
    0.08
    throp
    0.08
    ,is
    0.08
     anyway
    0.07
    iani
    0.07
    interpreter
    0.07
    ··
    0.07
     Crusher
    0.07
    iaux
    0.07
    Activations Density 0.090%

    No Known Activations