© 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. 91329
    Prev
    Next
    INDEX
    Explanations

    questions seeking clarification

    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
     either
    -0.16
     EITHER
    -0.16
     Either
    -0.15
    either
    -0.14
    Either
    -0.13
     ANY
    -0.11
    ä»»
    -0.11
    arte
    -0.11
    ipay
    -0.11
     whichever
    -0.11
    POSITIVE LOGITS
     something
    0.17
    ?↵↵
    0.14
     do
    0.13
     Something
    0.13
     ?↵↵
    0.13
    something
    0.12
     does
    0.12
    ?↵
    0.12
     nah
    0.12
    ?.
    0.11
    Activations Density 0.092%

    No Known Activations