© 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. 29937
    Prev
    Next
    INDEX
    Explanations

    URLs, abbreviations, or special characters

    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
     Deng
    -0.11
    ↵
    -0.11
    perms
    -0.09
     Osama
    -0.09
     ?>↵
    -0.09
    toc
    -0.09
    nbsp
    -0.09
     Nack
    -0.09
     tekst
    -0.09
     prec
    -0.08
    POSITIVE LOGITS
     condos
    0.10
    /screen
    0.10
    akest
    0.09
    emax
    0.09
     senate
    0.09
     expos
    0.09
     Famil
    0.09
    :v
    0.09
    ropri
    0.09
     wÅĤa
    0.09
    Activations Density 0.003%

    No Known Activations