© 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. 47301
    Prev
    Next
    INDEX
    Explanations

    numbers followed by hyphens and numbers

    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
    âĢ²
    -0.09
    âĢ³
    -0.09
     decades
    -0.07
     dimensional
    -0.07
    æľĪ
    -0.07
     unf
    -0.07
    agon
    -0.07
    ½
    -0.07
    arde
    -0.07
    enberg
    -0.07
    POSITIVE LOGITS
    -five
    0.23
    -two
    0.22
    -one
    0.21
    -six
    0.21
    -nine
    0.20
    -seven
    0.19
    -eight
    0.19
    -four
    0.19
    -three
    0.18
    -One
    0.17
    Activations Density 0.064%

    No Known Activations