© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 27913
    Prev
    Next
    INDEX
    Explanations

    states of being or becoming

    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
     Paw
    -0.11
     Spit
    -0.10
    aben
    -0.10
     inevitable
    -0.10
    adr
    -0.10
    XM
    -0.10
    seys
    -0.10
    l
    -0.10
    /if
    -0.10
     ceremon
    -0.10
    POSITIVE LOGITS
     grow
    0.11
     asleep
    0.10
     sleeps
    0.10
     malfunction
    0.10
     sleep
    0.09
     die
    0.09
     Brun
    0.09
     means
    0.09
     undergo
    0.09
    stead
    0.08
    Activations Density 0.031%

    No Known Activations