© 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. 113533
    Prev
    Next
    INDEX
    Explanations

    initialisms and abbreviations

    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
     fur
    -0.08
     budgets
    -0.08
    budget
    -0.08
     meno
    -0.08
    rok
    -0.08
    follower
    -0.08
    RAR
    -0.08
     noticeably
    -0.08
    ology
    -0.07
    mainwindow
    -0.07
    POSITIVE LOGITS
     abbreviation
    0.11
    /AFP
    0.10
     Meer
    0.10
     acronym
    0.10
     bent
    0.10
    overs
    0.10
    overe
    0.09
     retro
    0.09
    asy
    0.09
    pending
    0.09
    Activations Density 1.004%

    No Known Activations