© 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. 113331
    Prev
    Next
    INDEX
    Explanations

    click to enlarge or view below

    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
    ieux
    -0.11
     Cherry
    -0.11
    enco
    -0.10
     cherry
    -0.10
    igo
    -0.09
     Architecture
    -0.09
    anon
    -0.09
     Youtube
    -0.09
    /watch
    -0.09
    kul
    -0.09
    POSITIVE LOGITS
     above
    0.10
     itself
    0.09
    ibs
    0.09
     Sunrise
    0.09
    tract
    0.09
     navig
    0.09
     Qu
    0.08
    zed
    0.08
     vertically
    0.08
     latch
    0.08
    Activations Density 0.003%

    No Known Activations