© 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. 15887
    Prev
    Next
    INDEX
    Explanations

    ap followed by common endings

    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
    atra
    -0.11
    an
    -0.11
    on
    -0.11
    anke
    -0.11
    ede
    -0.10
    añ
    -0.10
    aname
    -0.09
    i
    -0.09
    o
    -0.09
    iet
    -0.09
    POSITIVE LOGITS
    ty
    0.10
    etag
    0.10
    rece
    0.10
     Gavin
    0.10
    fax
    0.10
    latin
    0.09
     Rocky
    0.09
    rstrip
    0.09
    Lit
    0.09
    ton
    0.09
    Activations Density 0.075%

    No Known Activations