© 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. 7876
    Prev
    Next
    INDEX
    Explanations

    numbers and symbols

    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
    499
    -0.10
    éĹ´
    -0.10
    Blob
    -0.10
     pris
    -0.09
    433
    -0.09
     pes
    -0.09
    sans
    -0.09
     Gaz
    -0.09
     Proceed
    -0.09
    rait
    -0.09
    POSITIVE LOGITS
    TEL
    0.09
     Hank
    0.09
     Breath
    0.09
     Rubio
    0.09
     extensive
    0.09
    ica
    0.09
    <_
    0.08
     birthdays
    0.08
     Av
    0.08
    WI
    0.08
    Activations Density 0.004%

    No Known Activations