© 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. 89373
    Prev
    Next
    INDEX
    Explanations

    US state and territory 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
    anzi
    -0.09
    ses
    -0.09
    isi
    -0.09
    anter
    -0.08
     UA
    -0.08
    ë
    -0.07
    ë¶Ģ
    -0.07
     double
    -0.07
    yg
    -0.07
     Rated
    -0.07
    POSITIVE LOGITS
     perc
    0.13
     acc
    0.12
     intox
    0.12
    tempt
    0.12
    ativ
    0.11
     assoc
    0.10
    \xc
    0.10
    Unnamed
    0.10
    prov
    0.10
    !!)↵
    0.10
    Activations Density 0.008%

    No Known Activations