© 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. 29212
    Prev
    Next
    INDEX
    Explanations

    book titles and technical terms

    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
     inaug
    -0.09
    ãĤ³ãĥ¡ãĥ³ãĥĪ
    -0.09
     <--
    -0.09
    ogo
    -0.08
     compl
    -0.08
    -blog
    -0.08
     Tre
    -0.08
     merry
    -0.08
    aller
    -0.08
    �t
    -0.07
    POSITIVE LOGITS
     noun
    0.12
    noun
    0.11
     adjective
    0.11
     Definition
    0.10
     definition
    0.09
     McInt
    0.09
     word
    0.09
    pedia
    0.09
     bah
    0.09
     verb
    0.09
    Activations Density 0.470%

    No Known Activations