© 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. 3873
    Prev
    Next
    INDEX
    Explanations

    number and abbreviation sequences

    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
     cole
    -0.10
    ocha
    -0.10
    andum
    -0.09
    izable
    -0.09
    bé
    -0.09
     nipples
    -0.09
     byÅĤ
    -0.09
    .reporting
    -0.09
    tesy
    -0.09
    mr
    -0.09
    POSITIVE LOGITS
    ften
    0.09
     Nam
    0.08
     Trad
    0.08
     bare
    0.07
    .bad
    0.07
     Bare
    0.07
    bsite
    0.07
     Em
    0.07
     hence
    0.07
    /Y
    0.07
    Activations Density 0.230%

    No Known Activations