© 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. 18208
    Prev
    Next
    INDEX
    Explanations

    or which

    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
    ERY
    -0.11
     impatient
    -0.11
    efe
    -0.11
     Sik
    -0.11
     consequ
    -0.11
    "d
    -0.11
    (rec
    -0.11
    erer
    -0.10
    oa
    -0.10
    ons
    -0.10
    POSITIVE LOGITS
     whatever
    0.11
     etc
    0.09
     whichever
    0.08
     knack
    0.08
     Bucc
    0.08
    Whatever
    0.08
     referring
    0.08
     famously
    0.08
     tally
    0.07
     Whatever
    0.07
    Activations Density 0.080%

    No Known Activations