© 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. 47589
    Prev
    Next
    INDEX
    Explanations

    and then what comes next

    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
     etiqu
    -0.19
     Hence
    -0.17
     upto
    -0.17
    Apart
    -0.16
     utmost
    -0.16
     irrespective
    -0.16
     hence
    -0.16
     functionalities
    -0.16
     equipments
    -0.16
     peculiar
    -0.14
    POSITIVE LOGITS
     decidedly
    0.20
     ostensibly
    0.18
     shorthand
    0.16
     glean
    0.15
     meld
    0.15
     cleanly
    0.14
    âĢ¦but
    0.14
     pared
    0.13
     disparate
    0.13
    —and
    0.13
    Activations Density 0.028%

    No Known Activations